Skip to main content

meshagent

Usage:
$ meshagent [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • version: Print the version
  • setup: Perform initial login and project/api key…
  • “: Trigger agent/tool calls in a room
  • “: Authenticate to meshagent
  • “: Manage or activate your meshagent projects
  • “: Manage or activate api-keys for your project
  • “: Inspect recent sessions and events
  • ask: Send a one-shot LLM prompt.
  • generate: Generate a participant token (JWT) from a…
  • “: Manage project webhooks
  • “: Manage services for your project
  • “: Build, run, and deploy packaged services.
  • “: Bridge MCP servers into MeshAgent rooms
  • “: Manage secrets for your project.
  • service: Run local helper HTTP services
  • service: Run local helper HTTP services
  • “: Create, list, and manage rooms in a project
  • “: Manage mailboxes for your project
  • “: Manage routes for your project
  • “: Manage registries for your project
  • build: Build a container image inside a room.
  • deploy: Create or update a room service from an…
  • “: Manage scheduled tasks for your project
  • “: Join a meeting transcriber to a room
  • forward: Forward a container port to localhost
  • “: Run an HTTP webserver connected to a…
  • “: Codex-backed agents
  • “: Connect agents and tools to a room
  • “: Join a voicebot to a room
  • “: Join a chatbot to a room
  • “: Join a process-backed agent to a room
  • “: Join a mailbot to a room
  • “: Join a taskrunner to a room
  • “: Join a worker agent to a room
  • “: Operate within a room
  • “: Local LLM proxy utilities

meshagent version

Print the version Usage:
$ meshagent version [OPTIONS]
Options:
  • --help: Show this message and exit.

meshagent setup

Perform initial login and project/api key activation. Usage:
$ meshagent setup [OPTIONS]
Options:
  • --api-url TEXT: Persist this API URL on the saved profile and use it for setup login.
  • --help: Show this message and exit.

meshagent

Trigger agent/tool calls in a room Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • tool: Send a call request to a tool webhook URL
  • agent: Send a call request to an agent webhook URL
  • toolkit: Send a call request to a toolkit webhook URL
  • schema: Send a call request to a schema webhook URL

meshagent tool

Send a call request to a tool webhook URL Usage:
$ meshagent  tool [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.

meshagent agent

Send a call request to an agent webhook URL Usage:
$ meshagent  agent [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.

meshagent toolkit

Send a call request to a toolkit webhook URL Usage:
$ meshagent  toolkit [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.

meshagent schema

Send a call request to a schema webhook URL Usage:
$ meshagent  schema [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.

meshagent

Authenticate to meshagent Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • login
  • logout
  • switch
  • whoami

meshagent login

Usage:
$ meshagent  login [OPTIONS]
Options:
  • --api-url TEXT: Persist this API URL on the saved profile and use it for this login.
  • --help: Show this message and exit.

meshagent logout

Usage:
$ meshagent  logout [OPTIONS]
Options:
  • --help: Show this message and exit.

meshagent switch

Usage:
$ meshagent  switch [OPTIONS] [PROFILE]
Arguments:
  • [PROFILE]: Saved profile user id or email. If omitted, saved profiles are listed.
Options:
  • --help: Show this message and exit.

meshagent whoami

Usage:
$ meshagent  whoami [OPTIONS]
Options:
  • --help: Show this message and exit.

meshagent

Manage or activate your meshagent projects Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • create: Create a new MeshAgent project.
  • list: List projects and mark the currently…
  • activate: Set the active project for subsequent CLI…

meshagent create

Create a new MeshAgent project. Usage:
$ meshagent  create [OPTIONS] NAME
Arguments:
  • NAME: [required]
Options:
  • --help: Show this message and exit.

meshagent list

List projects and mark the currently active one. Usage:
$ meshagent  list [OPTIONS]
Options:
  • -o, --output TEXT: output format [default: table]
  • --help: Show this message and exit.

meshagent activate

Set the active project for subsequent CLI commands. Usage:
$ meshagent  activate [OPTIONS] [PROJECT_ID]
Arguments:
  • [PROJECT_ID]
Options:
  • -i, --interactive: Interactively select or create a project
  • --help: Show this message and exit.

meshagent

Manage or activate api-keys for your project Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • list: List API keys for a project.
  • create: Create a new API key for a project.
  • show: Show the activated API key for a project.
  • env: Print the activated API key as a shell…
  • activate: Set the default API key for a project in…
  • delete: Delete an API key from a project.

meshagent list

List API keys for a project. Usage:
$ meshagent  list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -o, --output TEXT: output format [default: table]
  • --help: Show this message and exit.

meshagent create

Create a new API key for a project. Usage:
$ meshagent  create [OPTIONS] NAME
Arguments:
  • NAME: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --description TEXT: a description for the api key
  • --activate / --no-activate: use this key by default for commands that accept an API key [default: no-activate]
  • --silent / --no-silent: do not print api key [default: no-silent]
  • --help: Show this message and exit.

meshagent show

Show the activated API key for a project. Usage:
$ meshagent  show [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent env

Print the activated API key as a shell export snippet. Usage:
$ meshagent  env [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent activate

Set the default API key for a project in local CLI settings. Usage:
$ meshagent  activate [OPTIONS] KEY
Arguments:
  • KEY: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent delete

Delete an API key from a project. Usage:
$ meshagent  delete [OPTIONS] ID
Arguments:
  • ID: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent

Inspect recent sessions and events Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • list: List recent sessions
  • show: Show events for a session

meshagent list

List recent sessions Usage:
$ meshagent  list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --limit INTEGER RANGE: Maximum sessions to return (server max 1000) [default: 25; x>=1]
  • --room TEXT: Only include sessions for the given room name
  • --help: Show this message and exit.

meshagent show

Show events for a session Usage:
$ meshagent  show [OPTIONS] SESSION_ID
Arguments:
  • SESSION_ID: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent ask

Send a one-shot LLM prompt. Usage:
$ meshagent ask [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -m, --message TEXT: Prompt to send to the LLM
  • --format TEXT: Output format for non-interactive responses. [default: text]
  • --model TEXT: Name of the LLM model to use [default: gpt-5.4]
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.

meshagent generate

Generate a participant token (JWT) from a spec Usage:
$ meshagent generate [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -o, --output TEXT: File path to a file
  • -i, --input TEXT: File path to a token spec [required]
  • --key TEXT: an api key to sign the token with
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.

meshagent

Manage project webhooks Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • create: Create a webhook
  • list: List webhooks
  • delete: Delete a webhook

meshagent create

Create a webhook Usage:
$ meshagent  create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --name TEXT: Friendly name for the webhook [required]
  • --url TEXT: Target URL that will receive POSTs [required]
  • -e, --event TEXT: Event to subscribe to (repeat for multiple). [required]
  • TEXT: Optional description
  • --action TEXT: Optional action name delivered with each call
  • --payload TEXT: Optional JSON string sent as the body (merged with event payload).
  • --help: Show this message and exit.

meshagent list

List webhooks Usage:
$ meshagent  list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent delete

Delete a webhook Usage:
$ meshagent  delete [OPTIONS] WEBHOOK_ID
Arguments:
  • WEBHOOK_ID: ID of the webhook to delete [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent

Manage services for your project Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • spec: Render a service or template YAML spec…
  • create: Create a service attached to the project.
  • update: Create a service attached to the project.
  • validate: Validate a service spec from a YAML file.
  • create-template: Create a service from a ServiceTemplate spec.
  • update-template: Update a service using a ServiceTemplate…
  • validate-template: Validate a service template from a YAML file.
  • render-template: Render a service template with variables…
  • run: Run a local command and register it as a…
  • show: Show a services for the project.
  • list: List all services for the project.
  • delete: Delete a service.

meshagent spec

Render a service or template YAML spec without creating a service. Usage:
$ meshagent  spec [OPTIONS]
Options:
  • -f, --file TEXT: File path to a service definition
  • --url TEXT: URL to a service definition
  • --mcp TEXT: MCP server URL. Auto-discovers metadata and generates a service spec without creating it.
  • --format [service|template]: Output format. ‘service’ emits Service YAML. ‘template’ emits ServiceTemplate YAML. [default: service]
  • --service-id TEXT: Optional override for meshagent.service.id in metadata annotations.
  • --help: Show this message and exit.

meshagent create

Create a service attached to the project. Usage:
$ meshagent  create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -f, --file TEXT: File path to a service definition
  • --url TEXT: URL to a service definition
  • --mcp TEXT: MCP server URL. Auto-discovers OAuth metadata and creates an external MCP service configured for dynamic client registration.
  • --room TEXT: Room name
  • --global: Create the service globally instead of in a room
  • --service-id TEXT: Optional override for meshagent.service.id in metadata annotations.
  • --force: Ignore an existing service with the same meshagent.service.id.
  • --replace: Replace an existing service with the same meshagent.service.id.
  • --help: Show this message and exit.

meshagent update

Create a service attached to the project. Usage:
$ meshagent  update [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --id TEXT
  • -f, --file TEXT: File path to a service definition
  • --url TEXT: URL to a service definition
  • --mcp TEXT: MCP server URL. Auto-discovers OAuth metadata and builds an external MCP service configured for dynamic client registration.
  • --create / --no-create: create the service if it does not exist [default: no-create]
  • --room TEXT: Room name
  • --global: Update the global service instead of a room service
  • --service-id TEXT: Optional override for meshagent.service.id in metadata annotations.
  • --force: Ignore an existing service with the same meshagent.service.id.
  • --replace: Replace an existing service with the same meshagent.service.id.
  • --help: Show this message and exit.

meshagent validate

Validate a service spec from a YAML file. Usage:
$ meshagent  validate [OPTIONS]
Options:
  • -f, --file TEXT: File path to a service definition [required]
  • --help: Show this message and exit.

meshagent create-template

Create a service from a ServiceTemplate spec. Usage:
$ meshagent  create-template [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -f, --file TEXT: File path to a service template
  • --url TEXT: URL to a service template
  • --values-file TEXT: File path to template values
  • -v, --value TEXT: Template value override (key=value)
  • --room TEXT: Room name
  • --global: Create the service globally instead of in a room
  • --force: Ignore an existing service with the same meshagent.service.id.
  • --replace: Replace an existing service with the same meshagent.service.id.
  • --help: Show this message and exit.

meshagent update-template

Update a service using a ServiceTemplate spec. Usage:
$ meshagent  update-template [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --id TEXT
  • -f, --file TEXT: File path to a service template
  • --url TEXT: URL to a service template
  • --values-file TEXT: File path to template values
  • -v, --value TEXT: Template value override (key=value)
  • --create / --no-create: create the service if it does not exist [default: no-create]
  • --room TEXT: Room name
  • --global: Update the global service instead of a room service
  • --force: Ignore an existing service with the same meshagent.service.id.
  • --replace: Replace an existing service with the same meshagent.service.id.
  • --help: Show this message and exit.

meshagent validate-template

Validate a service template from a YAML file. Usage:
$ meshagent  validate-template [OPTIONS]
Options:
  • -f, --file TEXT: File path to a service template
  • --url TEXT: URL to a service template
  • --values-file TEXT: File path to template values
  • -v, --value TEXT: Template value override (key=value)
  • --help: Show this message and exit.

meshagent render-template

Render a service template with variables and print the rendered YAML. Usage:
$ meshagent  render-template [OPTIONS]
Options:
  • -f, --file TEXT: File path to a service template
  • --url TEXT: URL to a service template
  • --values-file TEXT: File path to template values
  • -v, --value TEXT: Template value override (key=value)
  • --help: Show this message and exit.

meshagent run

Run a local command and register it as a temporary room service. Usage:
$ meshagent  run [OPTIONS] COMMAND
Arguments:
  • COMMAND: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -p, --port INTEGER: a port number to run the agent on (will set MESHAGENT_PORT environment variable when launching the service)
  • --room TEXT: Room name
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.

meshagent show

Show a services for the project. Usage:
$ meshagent  show [OPTIONS] SERVICE_ID
Arguments:
  • SERVICE_ID: ID of the service to show [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name
  • --help: Show this message and exit.

meshagent list

List all services for the project. Usage:
$ meshagent  list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -o, --output TEXT: output format [default: table]
  • --room TEXT: Room name
  • --help: Show this message and exit.

meshagent delete

Delete a service. Usage:
$ meshagent  delete [OPTIONS] SERVICE_ID
Arguments:
  • SERVICE_ID: ID of the service to delete [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name
  • --help: Show this message and exit.

meshagent

Build, run, and deploy packaged services. Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • deploy: Deploy a packaged service into a room.
  • run: Run a packaged service container in a room.

meshagent deploy

Deploy a packaged service into a room. Usage:
$ meshagent  deploy [OPTIONS] MODULE
Arguments:
  • MODULE: Path to a Python file exporting a Package [required]
Options:
  • --room TEXT: Room name [default: (dynamic)]
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --name TEXT: Export name in the Python module [default: main]
  • --builder-name TEXT: Optional reusable builder name for package image builds.
  • --verbose: Print all files that will be added to the package.
  • --help: Show this message and exit.

meshagent run

Run a packaged service container in a room. Usage:
$ meshagent  run [OPTIONS] MODULE
Arguments:
  • MODULE: Path to a Python file exporting a Package [required]
Options:
  • --room TEXT: Room name [default: (dynamic)]
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --name TEXT: Export name in the Python module [default: main]
  • --builder-name TEXT: Optional reusable builder name for package image builds.
  • --verbose: Print all files that will be added to the package.
  • --help: Show this message and exit.

meshagent

Bridge MCP servers into MeshAgent rooms Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • sse: Connect an MCP server over SSE and…
  • http: Connect an MCP server over streamable HTTP…
  • stdio: Run an MCP server over stdio and register…
  • http-proxy: Expose a stdio MCP server over streamable…
  • sse-proxy: Expose a stdio MCP server over SSE
  • stdio-service: Run a stdio MCP server as an HTTP service

meshagent sse

Connect an MCP server over SSE and register it as a toolkit Usage:
$ meshagent  sse [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --name TEXT: Participant name [default: cli]
  • --role TEXT: [default: tool]
  • --url TEXT: SSE URL for the MCP server [required]
  • -H, --header TEXT: Request header (KEY:VALUE). Repeat for multiple headers
  • --header-secret TEXT: Header from secret (HEADER:FORMAT). FORMAT uses secret placeholders, e.g. Header:Bearer {my_secret}
  • --toolkit-name TEXT: Toolkit name to register in the room (default: mcp)
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.

meshagent http

Connect an MCP server over streamable HTTP and register it as a toolkit Usage:
$ meshagent  http [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --name TEXT: Participant name [default: cli]
  • --role TEXT: [default: tool]
  • --url TEXT: Streamable HTTP URL for the MCP server [required]
  • -H, --header TEXT: Request header (KEY:VALUE). Repeat for multiple headers
  • --header-secret TEXT: Header from secret (HEADER:FORMAT). FORMAT uses secret placeholders, e.g. Header:Bearer {my_secret}
  • --toolkit-name TEXT: Toolkit name to register in the room (default: mcp)
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.

meshagent stdio

Run an MCP server over stdio and register it as a toolkit Usage:
$ meshagent  stdio [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --name TEXT: Participant name [default: cli]
  • --role TEXT: [default: tool]
  • --command TEXT: Command to start an MCP server over stdio (quoted string) [required]
  • --toolkit-name TEXT: Toolkit name to register in the room (default: mcp)
  • -e, --env TEXT: KEY=VALUE
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.

meshagent http-proxy

Expose a stdio MCP server over streamable HTTP Usage:
$ meshagent  http-proxy [OPTIONS]
Options:
  • --command TEXT: Command to start the MCP server (stdio transport) [required]
  • --host TEXT: Host to bind the proxy server on
  • --port INTEGER: Port to bind the proxy server on
  • --path TEXT: HTTP path to mount the proxy server at
  • --name TEXT: Display name for the proxy server
  • -e, --env TEXT: KEY=VALUE
  • --help: Show this message and exit.

meshagent sse-proxy

Expose a stdio MCP server over SSE Usage:
$ meshagent  sse-proxy [OPTIONS]
Options:
  • --command TEXT: Command to start the MCP server (stdio transport) [required]
  • --host TEXT: Host to bind the proxy server on
  • --port INTEGER: Port to bind the proxy server on
  • --path TEXT: SSE path to mount the proxy at
  • --name TEXT: Display name for the proxy server
  • -e, --env TEXT: KEY=VALUE
  • --help: Show this message and exit.

meshagent stdio-service

Run a stdio MCP server as an HTTP service Usage:
$ meshagent  stdio-service [OPTIONS]
Options:
  • --command TEXT: Command to start an MCP server over stdio (quoted string) [required]
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --webhook-secret TEXT: Optional webhook secret for authenticating requests
  • --path TEXT: HTTP path to mount the service at
  • --toolkit-name TEXT: Toolkit name to expose (default: mcp)
  • -e, --env TEXT: KEY=VALUE
  • --help: Show this message and exit.

meshagent

Manage secrets for your project. Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • list: List all secrets in the project (typed as…
  • delete: Delete a secret.
  • “: Create or update environment-based…
  • “: Create or update environment-based…
  • “: Create or update a Docker registry pull…
  • “: Create or update an Azure Container…
  • “: Create or update a Google Artifact…

meshagent list

List all secrets in the project (typed as Docker/ACR/GAR or Keys secrets). Usage:
$ meshagent  list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent delete

Delete a secret. Usage:
$ meshagent  delete [OPTIONS] SECRET_ID
Arguments:
  • SECRET_ID: ID of the secret to delete [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent

Create or update environment-based key-value secrets. Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • create: Create a new ‘keys’ secret (opaque env-vars).
  • update: Update an existing ‘keys’ secret (opaque…

meshagent create

Create a new ‘keys’ secret (opaque env-vars). Usage:
$ meshagent   create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --name TEXT: Secret name [required]
  • --data TEXT: Format: key=value key2=value (space-separated) [required]
  • --help: Show this message and exit.

meshagent update

Update an existing ‘keys’ secret (opaque env-vars). Usage:
$ meshagent   update [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --secret-id TEXT: Existing secret ID [required]
  • --name TEXT: Secret name [required]
  • --data TEXT: Format: key=value key2=value (space-separated) [required]
  • --help: Show this message and exit.

meshagent

Create or update environment-based key-value secrets. Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • create: Create a new ‘keys’ secret (opaque env-vars).
  • update: Update an existing ‘keys’ secret (opaque…

meshagent create

Create a new ‘keys’ secret (opaque env-vars). Usage:
$ meshagent   create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --name TEXT: Secret name [required]
  • --data TEXT: Format: key=value key2=value (space-separated) [required]
  • --help: Show this message and exit.

meshagent update

Update an existing ‘keys’ secret (opaque env-vars). Usage:
$ meshagent   update [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --secret-id TEXT: Existing secret ID [required]
  • --name TEXT: Secret name [required]
  • --data TEXT: Format: key=value key2=value (space-separated) [required]
  • --help: Show this message and exit.

meshagent

Create or update a Docker registry pull secret. Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • create: Create a new Docker pull secret (generic).
  • update: Update an existing Docker pull secret…

meshagent create

Create a new Docker pull secret (generic). Usage:
$ meshagent   create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --name TEXT: Secret name [required]
  • --server TEXT: Docker registry server, e.g. index.docker.io [required]
  • --username TEXT: Registry user name [required]
  • --password TEXT: Registry password [required]
  • --email TEXT: User email for Docker config
  • --help: Show this message and exit.

meshagent update

Update an existing Docker pull secret (generic). Usage:
$ meshagent   update [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --secret-id TEXT: Existing secret ID [required]
  • --name TEXT: Secret name [required]
  • --server TEXT: Docker registry server [required]
  • --username TEXT: Registry user name [required]
  • --password TEXT: Registry password [required]
  • --email TEXT: User email for Docker config
  • --help: Show this message and exit.

meshagent

Create or update an Azure Container Registry pull secret. Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • create: Create a new ACR pull secret (defaults…
  • update: Update an existing ACR pull secret…

meshagent create

Create a new ACR pull secret (defaults email to ‘none@microsoft.com’). Usage:
$ meshagent   create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --name TEXT: Secret name [required]
  • --server TEXT: ACR server, e.g. myregistry.azurecr.io [required]
  • --username TEXT: Service principal ID [required]
  • --password TEXT: Service principal secret/password [required]
  • --help: Show this message and exit.

meshagent update

Update an existing ACR pull secret (defaults email to ‘none@microsoft.com’). Usage:
$ meshagent   update [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --secret-id TEXT: Existing secret ID [required]
  • --name TEXT: Secret name [required]
  • --server TEXT: ACR server, e.g. myregistry.azurecr.io [required]
  • --username TEXT: Service principal ID [required]
  • --password TEXT: Service principal secret/password [required]
  • --help: Show this message and exit.

meshagent

Create or update a Google Artifact Registry pull secret. Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • create: Create a new Google Artifact Registry pull…
  • update: Update an existing Google Artifact…

meshagent create

Create a new Google Artifact Registry pull secret. By default, sets email=‘none@google.com’, username=’_json_key’ Usage:
$ meshagent   create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --name TEXT: Secret name [required]
  • --server TEXT: GAR host, e.g. us-west1-docker.pkg.dev [required]
  • --json-key TEXT: Entire GCP service account JSON as string [required]
  • --help: Show this message and exit.

meshagent update

Update an existing Google Artifact Registry pull secret. Usage:
$ meshagent   update [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --secret-id TEXT: Existing secret ID [required]
  • --name TEXT: Secret name [required]
  • --server TEXT: GAR host, e.g. us-west1-docker.pkg.dev [required]
  • --json-key TEXT: Entire GCP service account JSON as string [required]
  • --help: Show this message and exit.

meshagent service

Run local helper HTTP services Usage:
$ meshagent service [OPTIONS]
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.

meshagent service

Run local helper HTTP services Usage:
$ meshagent service [OPTIONS]
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.

meshagent

Create, list, and manage rooms in a project Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • create: Create a room in the project.
  • delete: Delete a room by ID (or by name if —name…
  • update: Update a room’s name (ID is preferred;…
  • list: List rooms in the project.
  • get: Get a single room by name (handy for…

meshagent create

Create a room in the project. Usage:
$ meshagent  create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --name TEXT: Room name [required]
  • --if-not-exists / --no-if-not-exists: Do not error if the room already exists [default: no-if-not-exists]
  • --metadata TEXT: Optional JSON object for room metadata
  • --annotations TEXT: Optional JSON object for room annotations, e.g. {“meshagent.storage.class”:“ephemeral”}
  • --help: Show this message and exit.

meshagent delete

Delete a room by ID (or by name if —name is supplied). Usage:
$ meshagent  delete [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --id TEXT: Room ID (preferred)
  • --name TEXT
  • --help: Show this message and exit.

meshagent update

Update a room’s name (ID is preferred; name will be resolved to ID if needed). Usage:
$ meshagent  update [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --id TEXT: Room ID (preferred)
  • --name TEXT
  • --new-name TEXT: New room name [required]
  • --annotations TEXT: Optional JSON object for room annotations, e.g. {“meshagent.storage.class”:“ephemeral”}
  • --help: Show this message and exit.

meshagent list

List rooms in the project. Usage:
$ meshagent  list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -o, --output TEXT: output format [default: table]
  • --limit INTEGER RANGE: Max rooms to return [default: 50; 1<=x<=500]
  • --offset INTEGER RANGE: Offset for pagination [default: 0; x>=0]
  • --order-by TEXT: Order by column (e.g. “room_name”, “created_at”) [default: room_name]
  • --help: Show this message and exit.

meshagent get

Get a single room by name (handy for resolving the ID). Usage:
$ meshagent  get [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --name TEXT
  • --help: Show this message and exit.

meshagent

Manage mailboxes for your project Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • create: Create a mailbox attached to the project.
  • update: Update a mailbox routing configuration.
  • show: Show mailbox details.
  • list: List mailboxes for the project.
  • delete: Delete a mailbox.

meshagent create

Create a mailbox attached to the project. Usage:
$ meshagent  create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -a, --address TEXT: Mailbox email address (unique per project) [required]
  • --room TEXT: Room name
  • -q, --queue TEXT: Queue name to deliver inbound messages to [required]
  • --public: Queue name to deliver inbound messages to
  • -n, --annotations TEXT: annotations in json format {“name”:“value”}
  • --help: Show this message and exit.

meshagent update

Update a mailbox routing configuration. Usage:
$ meshagent  update [OPTIONS] ADDRESS
Arguments:
  • ADDRESS: Mailbox email address to update [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -r, --room TEXT: Room name to route inbound mail into
  • -q, --queue TEXT: Queue name to deliver inbound messages to
  • --public: Queue name to deliver inbound messages to
  • -n, --annotations TEXT: annotations in json format {“name”:“value”}
  • --help: Show this message and exit.

meshagent show

Show mailbox details. Usage:
$ meshagent  show [OPTIONS] ADDRESS
Arguments:
  • ADDRESS: Mailbox address to show [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent list

List mailboxes for the project. Usage:
$ meshagent  list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name
  • -o, --output TEXT: output format [default: table]
  • --help: Show this message and exit.

meshagent delete

Delete a mailbox. Usage:
$ meshagent  delete [OPTIONS] ADDRESS
Arguments:
  • ADDRESS: Mailbox address to delete [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent

Manage routes for your project Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • create: Create a route attached to the project.
  • update: Update a route configuration.
  • show: Show route details.
  • list: List routes for the project.
  • delete: Delete a route.

meshagent create

Create a route attached to the project. Usage:
$ meshagent  create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -d, --domain TEXT: Domain name to route (unique per project) [required]
  • --room TEXT: Room name
  • -p, --port TEXT: Published port to route to [required]
  • -n, --annotations TEXT: annotations in json format {“name”:“value”}
  • --help: Show this message and exit.

meshagent update

Update a route configuration. Usage:
$ meshagent  update [OPTIONS] DOMAIN
Arguments:
  • DOMAIN: Domain name to update [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -r, --room TEXT: Room name to route traffic into
  • -p, --port TEXT: Published port to route to
  • -n, --annotations TEXT: annotations in json format {“name”:“value”}
  • --help: Show this message and exit.

meshagent show

Show route details. Usage:
$ meshagent  show [OPTIONS] DOMAIN
Arguments:
  • DOMAIN: Domain name to show [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent list

List routes for the project. Usage:
$ meshagent  list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name
  • -o, --output TEXT: output format [default: table]
  • --help: Show this message and exit.

meshagent delete

Delete a route. Usage:
$ meshagent  delete [OPTIONS] DOMAIN
Arguments:
  • DOMAIN: Domain name to delete [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent

Manage registries for your project Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • create: Create a project registry repository.
  • update: Update a project registry repository.
  • show: Show registry details.
  • list: List registries for the project.
  • delete: Delete a project registry repository by id…

meshagent create

Create a project registry repository. Usage:
$ meshagent  create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -n, --name TEXT: Repository path in the public registry, for example ‘apps/demo’ [required]
  • -d, --description TEXT: Human-readable description
  • -a, --annotations TEXT: annotations in json format {“name”:“value”}
  • --help: Show this message and exit.

meshagent update

Update a project registry repository. Usage:
$ meshagent  update [OPTIONS] REPOSITORY_ID
Arguments:
  • REPOSITORY_ID: Repository id to update [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -n, --name TEXT: Updated repository path
  • -d, --description TEXT: Updated description
  • -a, --annotations TEXT: annotations in json format {“name”:“value”}
  • --help: Show this message and exit.

meshagent show

Show registry details. Usage:
$ meshagent  show [OPTIONS] REPOSITORY_ID
Arguments:
  • REPOSITORY_ID: Repository id to show [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent list

List registries for the project. Usage:
$ meshagent  list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -o, --output TEXT: output format [default: table]
  • --help: Show this message and exit.

meshagent delete

Delete a project registry repository by id or name. Usage:
$ meshagent  delete [OPTIONS] [REPOSITORY]
Arguments:
  • [REPOSITORY]: Repository id or name to delete
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --name TEXT: Repository name to delete
  • --help: Show this message and exit.

meshagent build

Build a container image inside a room. Usage:
$ meshagent build [OPTIONS] PATH
Arguments:
  • PATH: Local directory to stream as the build context. Format ‘<path>[:<mount>]’. Defaults mount to /context. [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used.
  • --room TEXT: Room name
  • --tag TEXT: Image tag to build. Supports <repository>:<tag>, <project-key>/<repository>:<tag>, or <registry>/<project-key>/<repository>:<tag>. Shorthand forms resolve against the configured MeshAgent registry. [required]
  • --context-path TEXT: Build context path inside the streamed build context (absolute path). Defaults to the PATH mount path.
  • --dockerfile-path TEXT: Optional Dockerfile path inside the streamed build context (absolute path).
  • --builder-name TEXT: Optional reusable builder name for streamed local builds.
  • --private / --public: Whether the build container is private to the participant [default: public]
  • --optimize / --no-optimize: Whether to optimize room image outputs to eStargz before publishing. Enabled by default. [default: optimize]
  • --cred TEXT: Docker creds (username,password) or (registry,username,password)
  • --help: Show this message and exit.

meshagent deploy

Create or update a room service from an image, optionally building it first. Usage:
$ meshagent deploy [OPTIONS] [PATH]
Arguments:
  • [PATH]: Local directory to stream as the build context before deploy. Format ‘<path>[:<mount>]’. Defaults mount to /context.
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used.
  • --room TEXT: Room name
  • --tag TEXT: Image tag to deploy, e.g. repo/name:tag. When used with PATH, shorthand <repository>:<tag> and <project-key>/<repository>:<tag> resolve against the configured MeshAgent registry. [required]
  • --context-path TEXT: Build context path inside the packed build context (absolute path). Only used with PATH.
  • --dockerfile-path TEXT: Optional Dockerfile path inside the packed build context (absolute path). Only used with PATH.
  • --optimize / --no-optimize: Whether to optimize room image outputs to eStargz during the build stage. Enabled by default. Only used with PATH. [default: optimize]
  • --cred TEXT: Docker creds (username,password) or (registry,username,password)
  • --builder-name TEXT: Optional reusable builder name for streamed local pack builds.
  • --domain TEXT: Create or update a room route for the deployed service. Requires exactly one published service port.
  • --liveness TEXT: HTTP path to use for service liveness checks. Defaults to / for new or missing HTTP liveness paths.
  • --room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • -e, --env TEXT: Set environment variable as KEY=VALUE
  • --env-secret TEXT: Set environment variable from a room secret as NAME=SECRET_ID
  • --identity TEXT: Identity name to use for —meshagent-token and —env-secret. Defaults to the current token identity or the derived service name.
  • --meshagent-token TEXT: Inject MESHAGENT_TOKEN using userDefault, agentDefault, full, or a JSON ApiScope object.
  • --private / --public: Whether published service ports should stay private or be public when they are created or updated. Defaults to private. [default: private]
  • --help: Show this message and exit.

meshagent

Manage scheduled tasks for your project Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • add: Add a scheduled task.
  • list: List scheduled tasks.
  • update: Update a scheduled task.
  • delete: Delete a scheduled task.

meshagent add

Add a scheduled task. Usage:
$ meshagent  add [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -r, --room TEXT: Room name
  • -q, --queue TEXT: Queue name to dispatch the task to [required]
  • -s, --schedule TEXT: Cron schedule for task execution [required]
  • --payload TEXT: JSON payload to enqueue (for example ’{“action”:“sync”}’)
  • --payload-file TEXT: Path to a file containing JSON payload
  • --id TEXT: Optional task id
  • --once: Run once and then deactivate
  • --active / --inactive: Initial active state [default: active]
  • -n, --annotations TEXT: annotations in json format {“name”:“value”}
  • --help: Show this message and exit.

meshagent list

List scheduled tasks. Usage:
$ meshagent  list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -r, --room TEXT: Filter by room name
  • --id, --task-id TEXT: Filter by scheduled task id
  • --active: Filter to active tasks only
  • --inactive: Filter to inactive tasks only
  • --limit INTEGER: Maximum number of tasks to return [default: 200]
  • --offset INTEGER: Row offset for pagination [default: 0]
  • -o, --output TEXT: output format [default: table]
  • --help: Show this message and exit.

meshagent update

Update a scheduled task. Usage:
$ meshagent  update [OPTIONS] TASK_ID
Arguments:
  • TASK_ID: Scheduled task id to update [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -r, --room TEXT: Updated room name
  • -q, --queue TEXT: Updated queue name
  • -s, --schedule TEXT: Updated cron schedule
  • --payload TEXT: Updated JSON payload to enqueue (for example ’{“action”:“sync”}’)
  • --payload-file TEXT: Path to a file containing updated JSON payload
  • --active: Mark the task active
  • --inactive: Mark the task inactive
  • -n, --annotations TEXT: annotations in json format {“name”:“value”}
  • --help: Show this message and exit.

meshagent delete

Delete a scheduled task. Usage:
$ meshagent  delete [OPTIONS] TASK_ID
Arguments:
  • TASK_ID: Scheduled task id to delete [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --help: Show this message and exit.

meshagent

Join a meeting transcriber to a room Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • join: Join a room and run the meeting…
  • service

meshagent join

Join a room and run the meeting transcriber agent. Usage:
$ meshagent  join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --agent-name TEXT: Name of the agent
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.

meshagent service

Usage:
$ meshagent  service [OPTIONS]
Options:
  • --agent-name TEXT: Name of the agent [required]
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at [default: /agent]
  • --help: Show this message and exit.

meshagent forward

Forward a container port to localhost Usage:
$ meshagent forward [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -r, --room TEXT: Room name containing the target container [required]
  • -n, --name TEXT: Container name to port-forward into
  • -c, --container-id TEXT: Container ID to port-forward into
  • -p, --port TEXT: Port mapping in the form LOCAL:REMOTE [required]
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.

meshagent

Run an HTTP webserver connected to a MeshAgent room. The webserver mounts static files/folders and python handlers from a routes file. Python handlers run with access to the active room and request objects. This lets you build web applications that take advantage of the MeshAgent room’s full feature set. Default routes file: webserver.yaml Add routes with the CLI: meshagent webserver add —path / —python handlers/home.py meshagent webserver add —path /assets —static ./public Start it locally by joining a room: meshagent webserver join —room my-room —agent-name my-web -f webserver.yaml —watch View the site from your local machine: http://127.0.0.1:8000 Use the host/port from webserver.yaml (or explicit —host/—port or —web-host/—web-port overrides). To make the site available outside your machine: meshagent webserver deploy —service-name my-web —agent-name my-web —room my-room -f webserver.yaml —website-path /website —domain my-web.meshagent.app --domain automatically creates or updates the route to the deployed room and webserver port. If the domain already targets a different room, deploy fails to avoid accidental repoints. Without --domain, create the route manually: meshagent route create —room my-room —port 8000 —domain my-web.meshagent.app Route source path rules:
  • python and static sources that start with / resolve to &#123;cwd&#125;/....
  • python and static sources without a leading / resolve relative to the routes file.
  • static supports both files and directories.
  • Set --app-dir to control Python import root (defaults to routes file directory).
Example routes file: kind: WebServer version: v1 host: 0.0.0.0 port: 8000 routes:
  • path: / methods:
    • GET python: handlers/home.py
  • path: /assets static: ./public
Example python handler (handlers/home.py): from aiohttp import web from meshagent.api import RoomClient async def handler( *, room: RoomClient, req: web.Request, ) -> web.StreamResponse: return web.Response(text=“hello”) Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • check: Validate a routes file and print the…
  • init: Create a routes file scaffold.
  • add: Add a route entry to the routes file.
  • join: Join a room and run the configured…
  • spec: Generate a service spec for deploying this…
  • deploy: Deploy this webserver as a service,…

meshagent check

Validate a routes file and print the resolved routes. Usage:
$ meshagent  check [OPTIONS]
Options:
  • -f TEXT: Path to routes file (default: webserver.yaml). YAML format: kind: WebServer, version: v1, host?, port?, routes: [{path, methods?, python?|static?}]. Route source resolution: ‘/x’ -> ‘{cwd}/x’; ‘x’ -> relative to routes file. ‘static’ supports files and directories. Use —app-dir to control Python import root (defaults to routes file directory). When —host/—port (or —web-host/—web-port) are not explicitly set, host/port from the routes file are used. Python handler signature: handler(*, room: RoomClient, req: web.Request) -> web.StreamResponse. Do not define METHOD/METHODS in handler files. [default: webserver.yaml]
  • --app-dir TEXT: Python import root for route handlers (similar to uvicorn —app-dir). Defaults to the routes file directory.
  • --help: Show this message and exit.

meshagent init

Create a routes file scaffold. Add routes with the CLI: meshagent webserver add —path / —python handlers/home.py meshagent webserver add —path /assets —static ./public Usage:
$ meshagent  init [OPTIONS]
Options:
  • -f TEXT: Path to routes file (default: webserver.yaml). YAML format: kind: WebServer, version: v1, host?, port?, routes: [{path, methods?, python?|static?}]. Route source resolution: ‘/x’ -> ‘{cwd}/x’; ‘x’ -> relative to routes file. ‘static’ supports files and directories. Use —app-dir to control Python import root (defaults to routes file directory). When —host/—port (or —web-host/—web-port) are not explicitly set, host/port from the routes file are used. Python handler signature: handler(*, room: RoomClient, req: web.Request) -> web.StreamResponse. Do not define METHOD/METHODS in handler files. [default: webserver.yaml]
  • --force: Overwrite existing routes file
  • --help: Show this message and exit.

meshagent add

Add a route entry to the routes file. Usage:
$ meshagent  add [OPTIONS]
Options:
  • --path TEXT: Route path to add (must start with ’/’) [required]
  • --python TEXT: Python handler path (relative to routes file); scaffolded if missing
  • --static TEXT: Static file or directory path (relative to routes file)
  • -m, --method TEXT: HTTP method for python routes (repeatable)
  • -f TEXT: Path to routes file (default: webserver.yaml). YAML format: kind: WebServer, version: v1, host?, port?, routes: [{path, methods?, python?|static?}]. Route source resolution: ‘/x’ -> ‘{cwd}/x’; ‘x’ -> relative to routes file. ‘static’ supports files and directories. Use —app-dir to control Python import root (defaults to routes file directory). When —host/—port (or —web-host/—web-port) are not explicitly set, host/port from the routes file are used. Python handler signature: handler(*, room: RoomClient, req: web.Request) -> web.StreamResponse. Do not define METHOD/METHODS in handler files. [default: webserver.yaml]
  • --help: Show this message and exit.

meshagent join

Join a room and run the configured webserver routes locally with optional hot reload. Usage:
$ meshagent  join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --agent-name TEXT: Name of the agent to call
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • --key TEXT: an api key to sign the token with
  • -f TEXT: Path to routes file (default: webserver.yaml). YAML format: kind: WebServer, version: v1, host?, port?, routes: [{path, methods?, python?|static?}]. Route source resolution: ‘/x’ -> ‘{cwd}/x’; ‘x’ -> relative to routes file. ‘static’ supports files and directories. Use —app-dir to control Python import root (defaults to routes file directory). When —host/—port (or —web-host/—web-port) are not explicitly set, host/port from the routes file are used. Python handler signature: handler(*, room: RoomClient, req: web.Request) -> web.StreamResponse. Do not define METHOD/METHODS in handler files. [default: webserver.yaml]
  • --app-dir TEXT: Python import root for route handlers (similar to uvicorn —app-dir). Defaults to the routes file directory.
  • --host TEXT: Host to bind the server [default: 127.0.0.1]
  • --port INTEGER: Port to bind the server [default: 8000]
  • --watch: Reload routes when the routes file or python handlers change
  • --help: Show this message and exit.

meshagent spec

Generate a service spec for deploying this webserver configuration. Usage:
$ meshagent  spec [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -f TEXT: Path to routes file (default: webserver.yaml). YAML format: kind: WebServer, version: v1, host?, port?, routes: [{path, methods?, python?|static?}]. Route source resolution: ‘/x’ -> ‘{cwd}/x’; ‘x’ -> relative to routes file. ‘static’ supports files and directories. Use —app-dir to control Python import root (defaults to routes file directory). When —host/—port (or —web-host/—web-port) are not explicitly set, host/port from the routes file are used. Python handler signature: handler(*, room: RoomClient, req: web.Request) -> web.StreamResponse. Do not define METHOD/METHODS in handler files. [default: webserver.yaml]
  • --app-dir TEXT: Python import root for route handlers (similar to uvicorn —app-dir). Defaults to the routes file directory.
  • --web-host TEXT: Host to bind the webserver [default: 0.0.0.0]
  • --web-port INTEGER: Port to bind the webserver [default: 8000]
  • --website-path TEXT: Required room storage subpath for route-referenced files (under the routes file directory) and the routes config file; adds a room storage mount so routes resolve in container (example: /website) [required]
  • --help: Show this message and exit.

meshagent deploy

Deploy this webserver as a service, updating an existing service with the same name. Usage:
$ meshagent  deploy [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -f TEXT: Path to routes file (default: webserver.yaml). YAML format: kind: WebServer, version: v1, host?, port?, routes: [{path, methods?, python?|static?}]. Route source resolution: ‘/x’ -> ‘{cwd}/x’; ‘x’ -> relative to routes file. ‘static’ supports files and directories. Use —app-dir to control Python import root (defaults to routes file directory). When —host/—port (or —web-host/—web-port) are not explicitly set, host/port from the routes file are used. Python handler signature: handler(*, room: RoomClient, req: web.Request) -> web.StreamResponse. Do not define METHOD/METHODS in handler files. [default: webserver.yaml]
  • --app-dir TEXT: Python import root for route handlers (similar to uvicorn —app-dir). Defaults to the routes file directory.
  • --web-host TEXT: Host to bind the webserver [default: 0.0.0.0]
  • --web-port INTEGER: Port to bind the webserver [default: 8000]
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: The name of a room to create the service for
  • --domain TEXT: Domain to create/update route for this deploy (must already target this room if it exists)
  • --website-path TEXT: Required room storage subpath to upload route-referenced files (under the routes file directory) and the routes config file into and mount at runtime (example: /website) [required]
  • --help: Show this message and exit.

meshagent

Codex-backed agents Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • “: Run codex chatbot agents
  • “: Run codex task-runner agents
  • “: Run codex worker agents

meshagent

Run codex chatbot agents Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • join: Join a room and run a Codex chatbot agent.
  • service
  • spec: Generate a service spec for deploying a…
  • deploy: Deploy a Codex chatbot service to a…
  • run: Join a room, start a Codex chatbot, and…
  • use: Send a one-shot or interactive message to…

meshagent join

Join a room and run a Codex chatbot agent. Usage:
$ meshagent   join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: Role to use for the agent token [default: agent]
  • --agent-name TEXT: Name of the agent to run
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --threading-mode [none|default-new]: Threading mode for chat UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for chat thread files. Defaults to .threads/<agent-name> when not provided.
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --key TEXT: An api key to sign the token with
  • --help: Show this message and exit.

meshagent service

Usage:
$ meshagent   service [OPTIONS]
Options:
  • --agent-name TEXT: Name of the agent to run [required]
  • --title TEXT: A friendly title for the chatbot
  • --description TEXT: A description for the chatbot
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --threading-mode [none|default-new]: Threading mode for chat UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for chat thread files. Defaults to .threads/<agent-name> when not provided.
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --help: Show this message and exit.

meshagent spec

Generate a service spec for deploying a Codex chatbot. Usage:
$ meshagent   spec [OPTIONS]
Options:
  • --service-name TEXT: Service name [required]
  • --service-description TEXT: Service description
  • --service-title TEXT: A display name for service
  • --agent-name TEXT: Name of the agent to run [required]
  • --title TEXT: A friendly title for the chatbot
  • --description TEXT: A description for the chatbot
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --threading-mode [none|default-new]: Threading mode for chat UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for chat thread files. Defaults to .threads/<agent-name> when not provided.
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --help: Show this message and exit.

meshagent deploy

Deploy a Codex chatbot service to a project or room. Usage:
$ meshagent   deploy [OPTIONS]
Options:
  • --service-name TEXT: Service name [required]
  • --service-description TEXT: Service description
  • --service-title TEXT: A display name for service
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: The name of a room to create the service for
  • --agent-name TEXT: Name of the agent to run [required]
  • --title TEXT: A friendly title for the chatbot
  • --description TEXT: A description for the chatbot
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --threading-mode [none|default-new]: Threading mode for chat UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for chat thread files. Defaults to .threads/<agent-name> when not provided.
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --help: Show this message and exit.

meshagent run

Join a room, start a Codex chatbot, and wait for messages. Usage:
$ meshagent   run [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: Role to use for the agent token [default: agent]
  • --agent-name TEXT: Name of the agent to run
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • --title TEXT: A friendly title for the chatbot
  • --description TEXT: A description for the chatbot
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --threading-mode [none|default-new]: Threading mode for chat UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for chat thread files. Defaults to .threads/<agent-name> when not provided.
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --key TEXT: An api key to sign the token with
  • --thread-path TEXT: Thread path to use for chat history
  • --message TEXT: Optional one-shot message
  • --use-web-search / --no-use-web-search: Request the web search tool
  • --use-image-gen / --no-use-image-gen: Request the image generation tool
  • --use-storage / --no-use-storage: Request the storage tool
  • --help: Show this message and exit.

meshagent use

Send a one-shot or interactive message to a running Codex chatbot. Usage:
$ meshagent   use [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --agent-name TEXT: Name of the agent to call
  • --thread-path TEXT: Thread path to use for chat history
  • --message TEXT: Optional one-shot message
  • --use-web-search / --no-use-web-search: Request the web search tool
  • --use-image-gen / --no-use-image-gen: Request the image generation tool
  • --use-storage / --no-use-storage: Request the storage tool
  • --help: Show this message and exit.

meshagent

Run codex task-runner agents Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • join: Join a room and run a Codex task-runner…
  • run: Join a room, start a Codex task-runner,…
  • service
  • spec: Generate a service spec for deploying a…
  • deploy: Deploy a Codex task-runner service to a…

meshagent join

Join a room and run a Codex task-runner agent. Usage:
$ meshagent   join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: Role to use for the agent token [default: agent]
  • --agent-name TEXT: Name of the agent to run
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --title TEXT: A friendly title for the task runner
  • --description TEXT: A description for the task runner
  • --supports-tools / --no-supports-tools: Whether the task runner supports tools [default: supports-tools]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --thread-name-rule TEXT: Rule for generating auto thread names (repeatable)
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --key TEXT: An api key to sign the token with
  • --help: Show this message and exit.

meshagent run

Join a room, start a Codex task-runner, and wait for tasks. Usage:
$ meshagent   run [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: Role to use for the agent token [default: agent]
  • --agent-name TEXT: Name of the agent to run
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --title TEXT: A friendly title for the task runner
  • --description TEXT: A description for the task runner
  • --supports-tools / --no-supports-tools: Whether the task runner supports tools [default: supports-tools]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --thread-name-rule TEXT: Rule for generating auto thread names (repeatable)
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --key TEXT: An api key to sign the token with
  • --input TEXT: JSON input for the task runner, or ’-’ for stdin
  • --with-caller / --no-with-caller: Whether to invoke the tool with the currently logged in user as the caller [default: with-caller]
  • --help: Show this message and exit.

meshagent service

Usage:
$ meshagent   service [OPTIONS]
Options:
  • --agent-name TEXT: Name of the agent to run [required]
  • --title TEXT: A friendly title for the task runner
  • --description TEXT: A description for the task runner
  • --supports-tools / --no-supports-tools: Whether the task runner supports tools [default: supports-tools]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --thread-name-rule TEXT: Rule for generating auto thread names (repeatable)
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --help: Show this message and exit.

meshagent spec

Generate a service spec for deploying a Codex task-runner. Usage:
$ meshagent   spec [OPTIONS]
Options:
  • --service-name TEXT: Service name [required]
  • --service-description TEXT: Service description
  • --service-title TEXT: A display name for service
  • --agent-name TEXT: Name of the agent to run [required]
  • --title TEXT: A friendly title for the task runner
  • --description TEXT: A description for the task runner
  • --supports-tools / --no-supports-tools: Whether the task runner supports tools [default: supports-tools]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --thread-name-rule TEXT: Rule for generating auto thread names (repeatable)
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --help: Show this message and exit.

meshagent deploy

Deploy a Codex task-runner service to a project or room. Usage:
$ meshagent   deploy [OPTIONS]
Options:
  • --service-name TEXT: Service name [required]
  • --service-description TEXT: Service description
  • --service-title TEXT: A display name for service
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: The name of a room to create the service for
  • --agent-name TEXT: Name of the agent to run [required]
  • --title TEXT: A friendly title for the task runner
  • --description TEXT: A description for the task runner
  • --supports-tools / --no-supports-tools: Whether the task runner supports tools [default: supports-tools]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --thread-name-rule TEXT: Rule for generating auto thread names (repeatable)
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --help: Show this message and exit.

meshagent

Run codex worker agents Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • join: Join a room and run a Codex worker agent.
  • service
  • spec: Generate a service spec for deploying a…
  • deploy: Deploy a Codex worker service to a project…

meshagent join

Join a room and run a Codex worker agent. Usage:
$ meshagent   join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: Role to use for the agent token [default: agent]
  • --agent-name TEXT: Name of the agent to run
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • --queue TEXT: The queue to consume [required]
  • --title TEXT: A friendly title for the worker
  • --description TEXT: A description for the worker
  • --prompt TEXT: Override prompt used for each message
  • --initial-message [summary|code|none]: Initial thread message mode: summary (LLM summary), code (markdown code block), or none [default: code]
  • --initial-message-from TEXT: Author name used for the initial thread message [default: worker]
  • --decision-model TEXT: Model used for summary decisions and payload summarization
  • --toolkit-name TEXT: Optional toolkit name to expose worker operations
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --key TEXT: An api key to sign the token with
  • --help: Show this message and exit.

meshagent service

Usage:
$ meshagent   service [OPTIONS]
Options:
  • --agent-name TEXT: Name of the agent to run [required]
  • --queue TEXT: The queue to consume [required]
  • --title TEXT: A friendly title for the worker
  • --description TEXT: A description for the worker
  • --prompt TEXT: Override prompt used for each message
  • --initial-message [summary|code|none]: Initial thread message mode: summary (LLM summary), code (markdown code block), or none [default: code]
  • --initial-message-from TEXT: Author name used for the initial thread message [default: worker]
  • --decision-model TEXT: Model used for summary decisions and payload summarization
  • --toolkit-name TEXT: Optional toolkit name to expose worker operations
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --help: Show this message and exit.

meshagent spec

Generate a service spec for deploying a Codex worker. Usage:
$ meshagent   spec [OPTIONS]
Options:
  • --service-name TEXT: Service name [required]
  • --service-description TEXT: Service description
  • --service-title TEXT: A display name for service
  • --agent-name TEXT: Name of the agent to run [required]
  • --queue TEXT: The queue to consume [required]
  • --title TEXT: A friendly title for the worker
  • --description TEXT: A description for the worker
  • --prompt TEXT: Override prompt used for each message
  • --initial-message [summary|code|none]: Initial thread message mode: summary (LLM summary), code (markdown code block), or none [default: code]
  • --initial-message-from TEXT: Author name used for the initial thread message [default: worker]
  • --decision-model TEXT: Model used for summary decisions and payload summarization
  • --toolkit-name TEXT: Optional toolkit name to expose worker operations
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --help: Show this message and exit.

meshagent deploy

Deploy a Codex worker service to a project or room. Usage:
$ meshagent   deploy [OPTIONS]
Options:
  • --service-name TEXT: Service name [required]
  • --service-description TEXT: Service description
  • --service-title TEXT: A display name for service
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: The name of a room to create the service for
  • --agent-name TEXT: Name of the agent to run [required]
  • --queue TEXT: The queue to consume [required]
  • --title TEXT: A friendly title for the worker
  • --description TEXT: A description for the worker
  • --prompt TEXT: Override prompt used for each message
  • --initial-message [summary|code|none]: Initial thread message mode: summary (LLM summary), code (markdown code block), or none [default: code]
  • --initial-message-from TEXT: Author name used for the initial thread message [default: worker]
  • --decision-model TEXT: Model used for summary decisions and payload summarization
  • --toolkit-name TEXT: Optional toolkit name to expose worker operations
  • -r, --rule TEXT: A system rule
  • -rr, --room-rules TEXT: A path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: The name or url of a required toolkit
  • -rs, --require-schema TEXT: The name or url of a required schema
  • --model TEXT: Codex model to use [default: gpt-5.4-codex]
  • --command TEXT: Command used to launch codex app-server
  • --ws-url TEXT: Websocket URL for an existing codex app-server
  • --codex-image TEXT: Container image used to run codex app-server; use ‘none’ to disable [default: meshagent/shell-codex:default]
  • --mount-room-path TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --mount-project-path TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --working-dir TEXT: Working directory passed to codex app-server
  • --approval-policy TEXT: Codex approval policy
  • --sandbox-policy TEXT: Codex sandbox policy
  • --mode [default|yolo|workspace-write|read-only]: Preset Codex mode: default | yolo | workspace-write | read-only
  • --skill-dir TEXT: An agent skills directory
  • --verbose: Log codex app-server JSON-RPC requests/responses
  • --delegate-shell-token: Pass the room token through to codex app-server as MESHAGENT_TOKEN / OPENAI_API_KEY / ANTHROPIC_API_KEY.
  • --copy-env TEXT: Copy local env vars into codex app-server env. Accepts comma-separated names and can be repeated.
  • --set-env TEXT: Set env vars in codex app-server env as NAME=VALUE. Can be repeated.
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --help: Show this message and exit.

meshagent

Connect agents and tools to a room Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • spec: Generate a combined service spec from…
  • deploy: Deploy a combined service from multiple…
  • service
  • join: Run multiple join commands together in one…

meshagent spec

Generate a combined service spec from multiple subcommands. Usage:
$ meshagent  spec [OPTIONS]
Options:
  • -c TEXT: a list of sub commands to run, seperated by semicolons
available sub commands: chatbot …; mailbot …; worker …; voicebot …; webserver …; python path-to-python-file.py —name=NameOfModule; chatbot, worker, mailbot, voicebot, and webserver command arguments mirror those of the respective meshagent chatbot service, meshagent worker service, meshagent mailbot service, meshagent voicebot service, and meshagent webserver service commands. [required]
  • --service-name TEXT: service name [required]
  • --agent-name TEXT: identity for injected MESHAGENT_TOKEN [required]
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --help: Show this message and exit.

meshagent deploy

Deploy a combined service from multiple subcommands. Usage:
$ meshagent  deploy [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -c TEXT: a list of sub commands to run, seperated by semicolons
available sub commands: chatbot …; mailbot …; worker …; voicebot …; webserver …; python path-to-python-file.py —name=NameOfModule; chatbot, worker, mailbot, voicebot, and webserver command arguments mirror those of the respective meshagent chatbot service, meshagent worker service, meshagent mailbot service, meshagent voicebot service, and meshagent webserver service commands. [required]
  • --service-name TEXT: service name [required]
  • --agent-name TEXT: identity for injected MESHAGENT_TOKEN [required]
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --room TEXT: The name of a room to create the service for
  • --help: Show this message and exit.

meshagent service

Usage:
$ meshagent  service [OPTIONS]
Options:
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • -c TEXT: a list of sub commands to run, seperated by semicolons
available sub commands: chatbot …; mailbot …; worker …; voicebot …; webserver …; python path-to-python-file.py —name=NameOfModule; chatbot, worker, mailbot, voicebot, and webserver command arguments mirror those of the respective meshagent chatbot service, meshagent worker service, meshagent mailbot service, meshagent voicebot service, and meshagent webserver service commands.
  • --help: Show this message and exit.

meshagent join

Run multiple join commands together in one process. Usage:
$ meshagent  join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • -c TEXT: a list of sub commands to run, seperated by semicolons
available sub commands: chatbot …; mailbot …; worker …; voicebot …; webserver …; python path-to-python-file.py —name=NameOfModule; chatbot, worker, mailbot, voicebot, and webserver command arguments mirror those of the respective meshagent chatbot service, meshagent worker service, meshagent mailbot service, meshagent voicebot service, and meshagent webserver service commands.
  • -p, --port INTEGER: a port number to run the agent on (will set MESHAGENT_PORT environment variable when launching the service)
  • --room TEXT: Room name [default: (dynamic)]
  • --key TEXT: an api key to sign the token with
  • --agent-name TEXT: Name of the agent to call
  • --help: Show this message and exit.

meshagent

Join a voicebot to a room Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • join: Join a room and run a voicebot agent.
  • service
  • spec: Generate a service spec for deploying a…
  • deploy: Deploy a voicebot service to a project or…

meshagent join

Join a room and run a voicebot agent. Usage:
$ meshagent  join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --agent-name TEXT: Name of the agent to call
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -rs, --require-schema TEXT: the name or url of a required schema
  • --auto-greet-message TEXT: Message to send automatically when the bot joins
  • --auto-greet-prompt TEXT: Prompt to generate an auto-greet message
  • --voice TEXT: OpenAI Realtime voice preset to use
  • --key TEXT: an api key to sign the token with
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --help: Show this message and exit.

meshagent service

Usage:
$ meshagent  service [OPTIONS]
Options:
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -rs, --require-schema TEXT: the name or url of a required schema
  • --auto-greet-message TEXT: Message to send automatically when the bot joins
  • --auto-greet-prompt TEXT: Prompt to generate an auto-greet message
  • --voice TEXT: OpenAI Realtime voice preset to use
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --help: Show this message and exit.

meshagent spec

Generate a service spec for deploying a voicebot. Usage:
$ meshagent  spec [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -rs, --require-schema TEXT: the name or url of a required schema
  • --auto-greet-message TEXT: Message to send automatically when the bot joins
  • --auto-greet-prompt TEXT: Prompt to generate an auto-greet message
  • --voice TEXT: OpenAI Realtime voice preset to use
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --help: Show this message and exit.

meshagent deploy

Deploy a voicebot service to a project or room. Usage:
$ meshagent  deploy [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -rs, --require-schema TEXT: the name or url of a required schema
  • --auto-greet-message TEXT: Message to send automatically when the bot joins
  • --auto-greet-prompt TEXT: Prompt to generate an auto-greet message
  • --voice TEXT: OpenAI Realtime voice preset to use
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: The name of a room to create the service for
  • --help: Show this message and exit.

meshagent

Join a chatbot to a room Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • join: Join a room and run a chatbot agent.
  • service
  • spec: Generate a service spec for deploying a…
  • deploy: Deploy a chatbot service to a project or…
  • run: Join a room, run the chatbot, and wait for…
  • use: Send a one-shot or interactive message to…

meshagent join

Join a room and run a chatbot agent. Usage:
$ meshagent  join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --agent-name TEXT: Name of the agent to call
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • -r, --rule TEXT: a system rule
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • --instructions TEXT: a path in the configured storage toolkit to a rules file that will be loaded at runtime
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --computer-use / --no-computer-use: Enable computer use [default: no-computer-use]
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --script-tool / --no-script-tool: Enable script tool calling [default: no-script-tool]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --mcp / --no-mcp: Enable mcp tool calling [default: no-mcp]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-tool-config-mount TEXT: Mount meshagent runtime config files read-only into <mount>
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --advanced-shell: Enable the managed container toolkit with start/list/stop/run tools.
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --document-authoring: Enable MeshDocument authoring
  • --discovery: Enable discovery of agents and tools
  • --working-dir TEXT: The default working directory for shell commands
  • --key TEXT: an api key to sign the token with
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --decision-model TEXT: Model used for thread naming and other secondary LLM decisions
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --always-reply / --no-always-reply: Always reply
  • --threading-mode [none|default-new]: Threading mode for thread UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for agent thread files. Defaults to .threads/<agent-name> when not provided.
  • --channel TEXT: Attach a channel to the agent process. Can be repeated. Currently supported: chat, mail:EMAIL_ADDRESS, queue:QUEUE_NAME, toolkit:NAME.
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: log all requests to the llm [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent service

Usage:
$ meshagent  service [OPTIONS]
Options:
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • --instructions TEXT: a path in the configured storage toolkit to a rules file that will be loaded at runtime
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --computer-use / --no-computer-use: Enable computer use [default: no-computer-use]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --script-tool / --no-script-tool: Enable script tool calling [default: no-script-tool]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --mcp / --no-mcp: Enable mcp tool calling [default: no-mcp]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-tool-config-mount TEXT: Mount meshagent runtime config files read-only into <mount>
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --advanced-shell: Enable the managed container toolkit with start/list/stop/run tools.
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --working-dir TEXT: The default working directory for shell commands
  • --require-document-authoring / --no-require-document-authoring: Enable document authoring [default: no-require-document-authoring]
  • --discovery: Enable discovery of agents and tools
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --decision-model TEXT: Model used for thread naming and other secondary LLM decisions
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --always-reply / --no-always-reply: Always reply
  • --threading-mode [none|default-new]: Threading mode for thread UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for agent thread files. Defaults to .threads/<agent-name> when not provided.
  • --channel TEXT: Attach a channel to the agent process. Can be repeated. Currently supported: chat, mail:EMAIL_ADDRESS, queue:QUEUE_NAME, toolkit:NAME.
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: log all requests to the llm [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent spec

Generate a service spec for deploying a chatbot. Usage:
$ meshagent  spec [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • --instructions TEXT: a path in the configured storage toolkit to a rules file that will be loaded at runtime
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --computer-use / --no-computer-use: Enable computer use [default: no-computer-use]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --script-tool / --no-script-tool: Enable script tool calling [default: no-script-tool]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --mcp / --no-mcp: Enable mcp tool calling [default: no-mcp]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-tool-config-mount TEXT: Mount meshagent runtime config files read-only into <mount>
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --advanced-shell: Enable the managed container toolkit with start/list/stop/run tools.
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --working-dir TEXT: The default working directory for shell commands
  • --require-document-authoring / --no-require-document-authoring: Enable document authoring [default: no-require-document-authoring]
  • --discovery: Enable discovery of agents and tools
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --decision-model TEXT: Model used for thread naming and other secondary LLM decisions
  • --always-reply / --no-always-reply: Always reply
  • --threading-mode [none|default-new]: Threading mode for thread UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for agent thread files. Defaults to .threads/<agent-name> when not provided.
  • --channel TEXT: Attach a channel to the agent process. Can be repeated. Currently supported: chat, mail:EMAIL_ADDRESS, queue:QUEUE_NAME, toolkit:NAME.
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: log all requests to the llm [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent deploy

Deploy a chatbot service to a project or room. Usage:
$ meshagent  deploy [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • --instructions TEXT: a path in the configured storage toolkit to a rules file that will be loaded at runtime
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --computer-use / --no-computer-use: Enable computer use [default: no-computer-use]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --script-tool / --no-script-tool: Enable script tool calling [default: no-script-tool]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --mcp / --no-mcp: Enable mcp tool calling [default: no-mcp]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-tool-config-mount TEXT: Mount meshagent runtime config files read-only into <mount>
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --advanced-shell: Enable the managed container toolkit with start/list/stop/run tools.
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --working-dir TEXT: The default working directory for shell commands
  • --require-document-authoring / --no-require-document-authoring: Enable document authoring [default: no-require-document-authoring]
  • --discovery: Enable discovery of agents and tools
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --decision-model TEXT: Model used for thread naming and other secondary LLM decisions
  • --always-reply / --no-always-reply: Always reply
  • --threading-mode [none|default-new]: Threading mode for thread UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for agent thread files. Defaults to .threads/<agent-name> when not provided.
  • --channel TEXT: Attach a channel to the agent process. Can be repeated. Currently supported: chat, mail:EMAIL_ADDRESS, queue:QUEUE_NAME, toolkit:NAME.
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: log all requests to the llm [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: The name of a room to create the service for
  • --help: Show this message and exit.

meshagent run

Join a room, run the chatbot, and wait for messages. Usage:
$ meshagent  run [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --agent-name TEXT: Name of the agent to call
  • -r, --rule TEXT: a system rule
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • --instructions TEXT: a path in the configured storage toolkit to a rules file that will be loaded at runtime
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --computer-use / --no-computer-use: Enable computer use [default: no-computer-use]
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --script-tool / --no-script-tool: Enable script tool calling [default: no-script-tool]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --mcp / --no-mcp: Enable mcp tool calling [default: no-mcp]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-tool-config-mount TEXT: Mount meshagent runtime config files read-only into <mount>
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --advanced-shell: Enable the managed container toolkit with start/list/stop/run tools.
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --document-authoring: Enable MeshDocument authoring
  • --discovery: Enable discovery of agents and tools
  • --working-dir TEXT: The default working directory for shell commands
  • --key TEXT: an api key to sign the token with
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --decision-model TEXT: Model used for thread naming and other secondary LLM decisions
  • --always-reply / --no-always-reply: Always reply
  • --threading-mode [none|default-new]: Threading mode for thread UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for agent thread files. Defaults to .threads/<agent-name> when not provided.
  • --channel TEXT: Attach a channel to the agent process. Can be repeated. Currently supported: chat, mail:EMAIL_ADDRESS, queue:QUEUE_NAME, toolkit:NAME.
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: log all requests to the llm [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --verbose: Enable verbose logging and disable default log suppression
  • --thread-path TEXT: log all requests to the llm
  • --message TEXT: the input message to use
  • --use-web-search / --no-use-web-search: request the web search tool
  • --use-image-gen / --no-use-image-gen: request the image gen tool
  • --use-storage / --no-use-storage: request the storage tool
  • --help: Show this message and exit.

meshagent use

Send a one-shot or interactive message to a running chatbot. Usage:
$ meshagent  use [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --agent-name TEXT: Name of the agent to call
  • --thread-path TEXT: log all requests to the llm
  • --message TEXT: the input message to use
  • --help: Show this message and exit.

meshagent

Join a process-backed agent to a room Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • join: Join a room and run a process-backed agent.
  • service: Add a process-backed agent service to the…
  • spec: Generate a service spec for deploying a…
  • deploy: Deploy a process-backed agent service.
  • run: Join a room, run a process-backed agent,…
  • use: Send a one-shot or interactive message to…

meshagent join

Join a room and run a process-backed agent. Usage:
$ meshagent  join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --agent-name TEXT: Name of the agent to call
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • -r, --rule TEXT: a system rule
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • --instructions TEXT: a path in the configured storage toolkit to a rules file that will be loaded at runtime
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --computer-use / --no-computer-use: Enable computer use [default: no-computer-use]
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --script-tool / --no-script-tool: Enable script tool calling [default: no-script-tool]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --mcp / --no-mcp: Enable mcp tool calling [default: no-mcp]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-tool-config-mount TEXT: Mount meshagent runtime config files read-only into <mount>
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --advanced-shell: Enable the managed container toolkit with start/list/stop/run tools.
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --document-authoring: Enable MeshDocument authoring
  • --discovery: Enable discovery of agents and tools
  • --working-dir TEXT: The default working directory for shell commands
  • --key TEXT: an api key to sign the token with
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --decision-model TEXT: Model used for thread naming and other secondary LLM decisions
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --always-reply / --no-always-reply: Always reply
  • --threading-mode [none|default-new]: Threading mode for thread UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for agent thread files. Defaults to .threads/<agent-name> when not provided.
  • --channel TEXT: Attach a channel to the agent process. Can be repeated. Currently supported: chat, mail:EMAIL_ADDRESS, queue:QUEUE_NAME, toolkit:NAME.
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: log all requests to the llm [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent service

Add a process-backed agent service to the host. Usage:
$ meshagent  service [OPTIONS]
Options:
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • --instructions TEXT: a path in the configured storage toolkit to a rules file that will be loaded at runtime
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --computer-use / --no-computer-use: Enable computer use [default: no-computer-use]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --script-tool / --no-script-tool: Enable script tool calling [default: no-script-tool]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --mcp / --no-mcp: Enable mcp tool calling [default: no-mcp]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-tool-config-mount TEXT: Mount meshagent runtime config files read-only into <mount>
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --advanced-shell: Enable the managed container toolkit with start/list/stop/run tools.
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --working-dir TEXT: The default working directory for shell commands
  • --require-document-authoring / --no-require-document-authoring: Enable document authoring [default: no-require-document-authoring]
  • --discovery: Enable discovery of agents and tools
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --decision-model TEXT: Model used for thread naming and other secondary LLM decisions
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --always-reply / --no-always-reply: Always reply
  • --threading-mode [none|default-new]: Threading mode for thread UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for agent thread files. Defaults to .threads/<agent-name> when not provided.
  • --channel TEXT: Attach a channel to the agent process. Can be repeated. Currently supported: chat, mail:EMAIL_ADDRESS, queue:QUEUE_NAME, toolkit:NAME.
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: log all requests to the llm [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent spec

Generate a service spec for deploying a process-backed agent. Usage:
$ meshagent  spec [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • --instructions TEXT: a path in the configured storage toolkit to a rules file that will be loaded at runtime
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --computer-use / --no-computer-use: Enable computer use [default: no-computer-use]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --script-tool / --no-script-tool: Enable script tool calling [default: no-script-tool]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --mcp / --no-mcp: Enable mcp tool calling [default: no-mcp]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-tool-config-mount TEXT: Mount meshagent runtime config files read-only into <mount>
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --advanced-shell: Enable the managed container toolkit with start/list/stop/run tools.
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --working-dir TEXT: The default working directory for shell commands
  • --require-document-authoring / --no-require-document-authoring: Enable document authoring [default: no-require-document-authoring]
  • --discovery: Enable discovery of agents and tools
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --decision-model TEXT: Model used for thread naming and other secondary LLM decisions
  • --always-reply / --no-always-reply: Always reply
  • --threading-mode [none|default-new]: Threading mode for thread UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for agent thread files. Defaults to .threads/<agent-name> when not provided.
  • --channel TEXT: Attach a channel to the agent process. Can be repeated. Currently supported: chat, mail:EMAIL_ADDRESS, queue:QUEUE_NAME, toolkit:NAME.
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: log all requests to the llm [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent deploy

Deploy a process-backed agent service. Usage:
$ meshagent  deploy [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • --instructions TEXT: a path in the configured storage toolkit to a rules file that will be loaded at runtime
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --computer-use / --no-computer-use: Enable computer use [default: no-computer-use]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --script-tool / --no-script-tool: Enable script tool calling [default: no-script-tool]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --mcp / --no-mcp: Enable mcp tool calling [default: no-mcp]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-tool-config-mount TEXT: Mount meshagent runtime config files read-only into <mount>
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --advanced-shell: Enable the managed container toolkit with start/list/stop/run tools.
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --working-dir TEXT: The default working directory for shell commands
  • --require-document-authoring / --no-require-document-authoring: Enable document authoring [default: no-require-document-authoring]
  • --discovery: Enable discovery of agents and tools
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --decision-model TEXT: Model used for thread naming and other secondary LLM decisions
  • --always-reply / --no-always-reply: Always reply
  • --threading-mode [none|default-new]: Threading mode for thread UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for agent thread files. Defaults to .threads/<agent-name> when not provided.
  • --channel TEXT: Attach a channel to the agent process. Can be repeated. Currently supported: chat, mail:EMAIL_ADDRESS, queue:QUEUE_NAME, toolkit:NAME.
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: log all requests to the llm [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: The name of a room to create the service for
  • --help: Show this message and exit.

meshagent run

Join a room, run a process-backed agent, and wait for messages. Usage:
$ meshagent  run [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --agent-name TEXT: Name of the agent to call
  • -r, --rule TEXT: a system rule
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • --instructions TEXT: a path in the configured storage toolkit to a rules file that will be loaded at runtime
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --computer-use / --no-computer-use: Enable computer use [default: no-computer-use]
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --script-tool / --no-script-tool: Enable script tool calling [default: no-script-tool]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --mcp / --no-mcp: Enable mcp tool calling [default: no-mcp]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-tool-config-mount TEXT: Mount meshagent runtime config files read-only into <mount>
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --advanced-shell: Enable the managed container toolkit with start/list/stop/run tools.
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --document-authoring: Enable MeshDocument authoring
  • --discovery: Enable discovery of agents and tools
  • --working-dir TEXT: The default working directory for shell commands
  • --key TEXT: an api key to sign the token with
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --decision-model TEXT: Model used for thread naming and other secondary LLM decisions
  • --always-reply / --no-always-reply: Always reply
  • --threading-mode [none|default-new]: Threading mode for thread UIs. Use ‘default-new’ to show a new-thread composer before loading a thread. [default: none]
  • --thread-dir TEXT: Thread directory for agent thread files. Defaults to .threads/<agent-name> when not provided.
  • --channel TEXT: Attach a channel to the agent process. Can be repeated. Currently supported: chat, mail:EMAIL_ADDRESS, queue:QUEUE_NAME, toolkit:NAME.
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: log all requests to the llm [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --verbose: Enable verbose logging and disable default log suppression
  • --thread-path TEXT: log all requests to the llm
  • --message TEXT: the input message to use
  • --use-web-search / --no-use-web-search: request the web search tool
  • --use-image-gen / --no-use-image-gen: request the image gen tool
  • --use-storage / --no-use-storage: request the storage tool
  • --help: Show this message and exit.

meshagent use

Send a one-shot or interactive message to a running process-backed agent. Usage:
$ meshagent  use [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --agent-name TEXT: Name of the agent to call
  • --thread-path TEXT: log all requests to the llm
  • --message TEXT: the input message to use
  • --help: Show this message and exit.

meshagent

Join a mailbot to a room Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • join: Join a room and run a mailbot agent.
  • service
  • spec: Generate a service spec for deploying a…
  • deploy: Deploy a mailbot service to a project or…

meshagent join

Join a room and run a mailbot agent. Usage:
$ meshagent  join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --agent-name TEXT: Name of the agent to call
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --shell: Enable function shell tool calling
  • --web-search: Enable web search tool calling
  • --web-fetch: Enable web fetch tool calling
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --apply-patch: Enable apply patch tool calling
  • --key TEXT: an api key to sign the token with
  • --queue TEXT: the name of the mail queue
  • --email-address TEXT: the email address of the agent [required]
  • --toolkit-name TEXT: the name of a toolkit to expose mail operations
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --whitelist TEXT: an email to whitelist
  • --storage: Enable storage toolkit
  • --read-only-storage: Enable read only storage toolkit
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --reply-all / --no-reply-all: Reply-all when responding to emails [default: no-reply-all]
  • --enable-attachments / --no-enable-attachments: Allow downloading and processing email attachments [default: no-enable-attachments]
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent service

Usage:
$ meshagent  service [OPTIONS]
Options:
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --shell: Enable function shell tool calling
  • --web-search: Enable web search tool calling
  • --web-fetch: Enable web fetch tool calling
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --apply-patch: Enable apply patch tool calling
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --queue TEXT: the name of the mail queue
  • --email-address TEXT: the email address of the agent [required]
  • --toolkit-name TEXT: the name of a toolkit to expose mail operations
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --whitelist TEXT: an email to whitelist
  • --storage: Enable storage toolkit
  • --read-only-storage: Enable read only storage toolkit
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --reply-all / --no-reply-all: Reply-all when responding to emails [default: no-reply-all]
  • --enable-attachments / --no-enable-attachments: Allow downloading and processing email attachments [default: no-enable-attachments]
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent spec

Generate a service spec for deploying a mailbot. Usage:
$ meshagent  spec [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --shell: Enable function shell tool calling
  • --web-search: Enable web search tool calling
  • --web-fetch: Enable web fetch tool calling
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --apply-patch: Enable apply patch tool calling
  • --queue TEXT: the name of the mail queue
  • --email-address TEXT: the email address of the agent [required]
  • --toolkit-name TEXT: the name of a toolkit to expose mail operations
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --whitelist TEXT: an email to whitelist
  • --storage: Enable storage toolkit
  • --read-only-storage: Enable read only storage toolkit
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --reply-all / --no-reply-all: Reply-all when responding to emails [default: no-reply-all]
  • --enable-attachments / --no-enable-attachments: Allow downloading and processing email attachments [default: no-enable-attachments]
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent deploy

Deploy a mailbot service to a project or room. Usage:
$ meshagent  deploy [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the chatbot [default: gpt-5.4]
  • --shell: Enable function shell tool calling
  • --web-search: Enable web search tool calling
  • --web-fetch: Enable web fetch tool calling
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --apply-patch: Enable apply patch tool calling
  • --queue TEXT: the name of the mail queue
  • --email-address TEXT: the email address of the agent [required]
  • --toolkit-name TEXT: the name of a toolkit to expose mail operations
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --whitelist TEXT: an email to whitelist
  • --storage: Enable storage toolkit
  • --read-only-storage: Enable read only storage toolkit
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Use a specific database namespace
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --reply-all / --no-reply-all: Reply-all when responding to emails [default: no-reply-all]
  • --enable-attachments / --no-enable-attachments: Allow downloading and processing email attachments [default: no-enable-attachments]
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: The name of a room to create the service for
  • --help: Show this message and exit.

meshagent

Join a taskrunner to a room Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • join: Join a room and run a task-runner agent.
  • run: Join a room, run the task-runner, and wait…
  • service
  • spec: Generate a service spec for deploying a…
  • deploy: Deploy a task-runner service to a project…

meshagent join

Join a room and run a task-runner agent. Usage:
$ meshagent  join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --agent-name TEXT: Name of the agent to call
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • -r, --rule TEXT: a system rule
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the task runner [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Database namespace (e.g. foo::bar)
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --document-authoring: Enable MeshDocument authoring
  • --discovery: Enable discovery of agents and tools
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --key TEXT: an api key to sign the token with
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --output-schema TEXT: an output schema to use
  • --output-schema-path TEXT: the path or url to output schema to use
  • -a, --annotations TEXT: annotations in json format {“name”:“value”} [default: {“meshagent.task-runner.attachment-format”:“tar”}]
  • --title TEXT: a friendly name for the task runner
  • --description TEXT: a description for the task runner
  • --allow-model-selection / --no-allow-model-selection: a description for the task runner [default: allow-model-selection]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --thread-name-rule TEXT: Rule for generating auto thread names (repeatable)
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent run

Join a room, run the task-runner, and wait for tasks. Usage:
$ meshagent  run [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --agent-name TEXT: Name of the agent to call
  • -r, --rule TEXT: a system rule
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the task runner [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Database namespace (e.g. foo::bar)
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --document-authoring: Enable MeshDocument authoring
  • --discovery: Enable discovery of agents and tools
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --key TEXT: an api key to sign the token with
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --output-schema TEXT: an output schema to use
  • --output-schema-path TEXT: the path or url to output schema to use
  • -a, --annotations TEXT: annotations in json format {“name”:“value”} [default: {“meshagent.task-runner.attachment-format”:“tar”}]
  • --title TEXT: a friendly name for the task runner
  • --description TEXT: a description for the task runner
  • --allow-model-selection / --no-allow-model-selection: a description for the task runner [default: allow-model-selection]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --thread-name-rule TEXT: Rule for generating auto thread names (repeatable)
  • --input TEXT: json input for the task runner, or ’-’ for stdin
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --verbose: Enable verbose logging and disable default log suppression
  • --with-caller / --no-with-caller: whether to invoke the tool with the currently logged in user as the caller [default: with-caller]
  • --help: Show this message and exit.

meshagent service

Usage:
$ meshagent  service [OPTIONS]
Options:
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the task runner [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Database namespace (e.g. foo::bar)
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --document-authoring: Enable document authoring
  • --discovery: Enable discovery of agents and tools
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --output-schema TEXT: an output schema to use
  • --output-schema-path TEXT: the path or url to output schema to use
  • -a, --annotations TEXT: annotations in json format {“name”:“value”} [default: {“meshagent.task-runner.attachment-format”:“tar”}]
  • --title TEXT: a friendly name for the task runner
  • --description TEXT: a description for the task runner
  • --allow-model-selection / --no-allow-model-selection: a description for the task runner [default: allow-model-selection]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --thread-name-rule TEXT: Rule for generating auto thread names (repeatable)
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent spec

Generate a service spec for deploying a task-runner. Usage:
$ meshagent  spec [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the task runner [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Database namespace (e.g. foo::bar)
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --document-authoring: Enable document authoring
  • --discovery: Enable discovery of agents and tools
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --output-schema TEXT: an output schema to use
  • --output-schema-path TEXT: the path or url to output schema to use
  • -a, --annotations TEXT: annotations in json format {“name”:“value”} [default: {“meshagent.task-runner.attachment-format”:“tar”}]
  • --title TEXT: a friendly name for the task runner
  • --description TEXT: a description for the task runner
  • --allow-model-selection / --no-allow-model-selection: a description for the task runner [default: allow-model-selection]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --thread-name-rule TEXT: Rule for generating auto thread names (repeatable)
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent deploy

Deploy a task-runner service to a project or room. Usage:
$ meshagent  deploy [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the agent to call [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rr, --room-rules TEXT: a path to a rules file within the room that can be used to customize the agent’s behavior
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use for the task runner [default: gpt-5.4]
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --table-read TEXT: Enable table read tools for a specific table
  • --table-write TEXT: Enable table write tools for a specific table
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Database namespace (e.g. foo::bar)
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --document-authoring: Enable document authoring
  • --discovery: Enable discovery of agents and tools
  • --llm-participant TEXT: Delegate LLM interactions to a remote participant
  • --output-schema TEXT: an output schema to use
  • --output-schema-path TEXT: the path or url to output schema to use
  • -a, --annotations TEXT: annotations in json format {“name”:“value”} [default: {“meshagent.task-runner.attachment-format”:“tar”}]
  • --title TEXT: a friendly name for the task runner
  • --description TEXT: a description for the task runner
  • --allow-model-selection / --no-allow-model-selection: a description for the task runner [default: allow-model-selection]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --thread-name-rule TEXT: Rule for generating auto thread names (repeatable)
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: The name of a room to create the service for
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --help: Show this message and exit.

meshagent

Join a worker agent to a room Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • join: Join a room and run a worker agent.
  • service
  • spec: Generate a service spec for deploying a…
  • deploy: Deploy a worker service to a project or room.

meshagent join

Join a room and run a worker agent. Usage:
$ meshagent  join [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --agent-name TEXT: Name of the worker agent
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use [default: gpt-5.4]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --initial-message [summary|code|none]: Initial thread message mode: summary (LLM summary), code (markdown code block), or none [default: code]
  • --initial-message-from TEXT: Author name used for the initial thread message [default: worker]
  • --decision-model TEXT: Model used for summary decisions and payload summarization
  • --key TEXT: an api key to sign the token with
  • --queue TEXT: the queue to consume [required]
  • --toolkit-name TEXT: optional toolkit name to expose worker operations
  • -rr, --room-rules TEXT: path(s) in room storage to load rules from
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --read-only-storage: Enable read only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Database namespace (e.g. foo::bar)
  • --table-read TEXT: Enable table read tools for these tables
  • --table-write TEXT: Enable table write tools for these tables
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --title TEXT: a display name for the agent
  • --description TEXT: a description for the agent
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --prompt TEXT: a prompt to use for the worker
  • --help: Show this message and exit.

meshagent service

Usage:
$ meshagent  service [OPTIONS]
Options:
  • --agent-name TEXT: Name of the worker agent [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use [default: gpt-5.4]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --initial-message [summary|code|none]: Initial thread message mode: summary (LLM summary), code (markdown code block), or none [default: code]
  • --initial-message-from TEXT: Author name used for the initial thread message [default: worker]
  • --decision-model TEXT: Model used for summary decisions and payload summarization
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --host TEXT: Host to bind the service on
  • --port INTEGER: Port to bind the service on
  • --path TEXT: HTTP path to mount the service at
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --queue TEXT: the queue to consume [required]
  • --toolkit-name TEXT: Toolkit name to expose (optional)
  • -rr, --room-rules TEXT: Path(s) to rules files inside the room
  • --read-only-storage: Require read-only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Database namespace (e.g. foo::bar)
  • --table-read TEXT: Require table read tool for table (repeatable)
  • --table-write TEXT: Require table write tool for table (repeatable)
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --title TEXT: a display name for the agent
  • --description TEXT: a description for the agent
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --prompt TEXT: a prompt to use for the worker
  • --help: Show this message and exit.

meshagent spec

Generate a service spec for deploying a worker. Usage:
$ meshagent  spec [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the worker agent [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use [default: gpt-5.4]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --initial-message [summary|code|none]: Initial thread message mode: summary (LLM summary), code (markdown code block), or none [default: code]
  • --initial-message-from TEXT: Author name used for the initial thread message [default: worker]
  • --decision-model TEXT: Model used for summary decisions and payload summarization
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --queue TEXT: the queue to consume [required]
  • --toolkit-name TEXT: Toolkit name to expose (optional)
  • -rr, --room-rules TEXT: Path(s) to rules files inside the room
  • --read-only-storage: Require read-only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Database namespace (e.g. foo::bar)
  • --table-read TEXT: Require table read tool for table (repeatable)
  • --table-write TEXT: Require table write tool for table (repeatable)
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --title TEXT: a display name for the agent
  • --description TEXT: a description for the agent
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --prompt TEXT: a prompt to use for the worker
  • --help: Show this message and exit.

meshagent deploy

Deploy a worker service to a project or room. Usage:
$ meshagent  deploy [OPTIONS]
Options:
  • --service-name TEXT: service name
  • --service-description TEXT: service description
  • --service-title TEXT: a display name for the service
  • --agent-name TEXT: Name of the worker agent [required]
  • -r, --rule TEXT: a system rule
  • --rules-file TEXT
  • -rt, --require-toolkit TEXT: the name or url of a required toolkit
  • -s, --schema TEXT: the name or url of a required schema
  • --model TEXT: Name of the LLM model to use [default: gpt-5.4]
  • --threading-mode [auto|manual|none]: Threading mode: none (no persistence), manual (input path), or auto (LLM-selected thread path) [default: none]
  • --thread-dir TEXT: Thread directory for auto mode; thread path is <thread_dir>/<name>.thread [default: .threads]
  • --initial-message [summary|code|none]: Initial thread message mode: summary (LLM summary), code (markdown code block), or none [default: code]
  • --initial-message-from TEXT: Author name used for the initial thread message [default: worker]
  • --decision-model TEXT: Model used for summary decisions and payload summarization
  • --image-generation TEXT: Name of an image gen model
  • --shell / --no-shell: Enable function shell tool calling [default: no-shell]
  • --apply-patch / --no-apply-patch: Enable apply patch tool [default: no-apply-patch]
  • --web-search / --no-web-search: Enable web search tool calling [default: no-web-search]
  • --web-fetch / --no-web-fetch: Enable web fetch tool calling [default: no-web-fetch]
  • --discover-script-tools / --no-discover-script-tools: Automatically add script tools from the room [default: no-discover-script-tools]
  • --storage / --no-storage: Enable storage toolkit [default: no-storage]
  • --storage-tool-local-path TEXT: Mount local path as <source>:<mount>[:ro|rw]
  • --storage-tool-room-path TEXT: Mount room path as <source>:<mount>[:ro|rw]
  • --shell-room-mount TEXT: Mount room storage as <source>:<mount>[:ro|rw]
  • --shell-project-mount TEXT: Mount project storage as <source>:<mount>[:ro|rw]
  • --shell-empty-dir-mount TEXT: Mount empty dir at <mount>[:ro|rw]
  • --queue TEXT: the queue to consume [required]
  • --toolkit-name TEXT: Toolkit name to expose (optional)
  • -rr, --room-rules TEXT: Path(s) to rules files inside the room
  • --read-only-storage: Require read-only storage toolkit
  • --time: Enable time/datetime tools [default: True]
  • --uuid: Enable UUID generation tools
  • --use-memory TEXT: Use memories toolkit for <name> or <namespace>/<name>
  • --memory-model TEXT: Model name for memory LLM ingestion
  • --database-namespace TEXT: Database namespace (e.g. foo::bar)
  • --table-read TEXT: Require table read tool for table (repeatable)
  • --table-write TEXT: Require table write tool for table (repeatable)
  • --computer-use: Enable computer use
  • --starting-url TEXT: Initial URL to open when starting a computer-use browser session
  • --allow-goto-url: Expose the goto URL helper tool for computer use
  • --title TEXT: a display name for the agent
  • --description TEXT: a description for the agent
  • --working-dir TEXT: The default working directory for shell commands
  • --skill-dir TEXT: an agent skills directory
  • --shell-image TEXT: an image tag to use to run shell commands in
  • --shell-image-mount TEXT: Mount image as <image>=<mount>[:ro|rw]
  • --delegate-shell-token / --no-delegate-shell-token: Delegate the room token to shell tools [default: no-delegate-shell-token]
  • --shell-copy-env TEXT: Copy local env vars into shell tool env. Accepts comma-separated names and can be repeated.
  • --shell-set-env TEXT: Set env vars in shell tool env as NAME=VALUE. Can be repeated.
  • --log-llm-requests / --no-log-llm-requests: log all requests to the llm [default: no-log-llm-requests]
  • --prompt TEXT: a prompt to use for the worker
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: The name of a room to create the service for
  • --help: Show this message and exit.

meshagent

Operate within a room Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • “: Interact with agents and toolkits in a room
  • “: Interact with agents and toolkits in a room
  • “: Manage room-scoped secrets and OAuth flows
  • “: Manage room-scoped secrets and OAuth flows
  • “: Use queues in a room
  • “: Send and receive messages in a room
  • “: Manage storage for a room
  • “: Manage services inside a room
  • “: Manage services inside a room
  • watch: Stream developer logs from a room
  • “: Manage database tables in a room
  • “: Manage room memories
  • “: Manage containers and images inside a room
  • “: Inspect and update mesh documents in a room
  • connect: Connect to a room and run a local command…

meshagent

Interact with agents and toolkits in a room Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • invoke-tool: Invoke a specific tool from a toolkit
  • list-toolkits: List toolkits (and tools) available in the…
  • “: Trigger agent/tool calls in a room

meshagent invoke-tool

Invoke a specific tool from a toolkit Usage:
$ meshagent   invoke-tool [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --toolkit TEXT: Toolkit name [required]
  • --tool TEXT: Tool name [required]
  • --arguments TEXT: JSON string with arguments for the tool [required]
  • --participant-id TEXT: Optional participant ID to invoke the tool on
  • --on-behalf-of-id TEXT: Optional ‘on_behalf_of’ participant ID
  • --caller-context TEXT: Optional JSON for caller context
  • --timeout INTEGER: How long to wait for the toolkit if the toolkit is not in the room [default: 30]
  • --help: Show this message and exit.

meshagent list-toolkits

List toolkits (and tools) available in the room Usage:
$ meshagent   list-toolkits [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: user]
  • --participant-id TEXT: Optional participant ID
  • --help: Show this message and exit.

meshagent

Trigger agent/tool calls in a room Usage:
$ meshagent    [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • tool: Send a call request to a tool webhook URL
  • agent: Send a call request to an agent webhook URL
  • toolkit: Send a call request to a toolkit webhook URL
  • schema: Send a call request to a schema webhook URL
meshagent tool
Send a call request to a tool webhook URL Usage:
$ meshagent    tool [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.
meshagent agent
Send a call request to an agent webhook URL Usage:
$ meshagent    agent [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.
meshagent toolkit
Send a call request to a toolkit webhook URL Usage:
$ meshagent    toolkit [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.
meshagent schema
Send a call request to a schema webhook URL Usage:
$ meshagent    schema [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.

meshagent

Interact with agents and toolkits in a room Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • invoke-tool: Invoke a specific tool from a toolkit
  • list-toolkits: List toolkits (and tools) available in the…
  • “: Trigger agent/tool calls in a room

meshagent invoke-tool

Invoke a specific tool from a toolkit Usage:
$ meshagent   invoke-tool [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --toolkit TEXT: Toolkit name [required]
  • --tool TEXT: Tool name [required]
  • --arguments TEXT: JSON string with arguments for the tool [required]
  • --participant-id TEXT: Optional participant ID to invoke the tool on
  • --on-behalf-of-id TEXT: Optional ‘on_behalf_of’ participant ID
  • --caller-context TEXT: Optional JSON for caller context
  • --timeout INTEGER: How long to wait for the toolkit if the toolkit is not in the room [default: 30]
  • --help: Show this message and exit.

meshagent list-toolkits

List toolkits (and tools) available in the room Usage:
$ meshagent   list-toolkits [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: user]
  • --participant-id TEXT: Optional participant ID
  • --help: Show this message and exit.

meshagent

Trigger agent/tool calls in a room Usage:
$ meshagent    [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • tool: Send a call request to a tool webhook URL
  • agent: Send a call request to an agent webhook URL
  • toolkit: Send a call request to a toolkit webhook URL
  • schema: Send a call request to a schema webhook URL
meshagent tool
Send a call request to a tool webhook URL Usage:
$ meshagent    tool [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.
meshagent agent
Send a call request to an agent webhook URL Usage:
$ meshagent    agent [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.
meshagent toolkit
Send a call request to a toolkit webhook URL Usage:
$ meshagent    toolkit [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.
meshagent schema
Send a call request to a schema webhook URL Usage:
$ meshagent    schema [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --role TEXT: [default: agent]
  • --local / --no-local
  • --participant-name TEXT: the participant name to be used by the callee
  • --url TEXT: URL the agent should call [required]
  • --arguments TEXT: JSON string with arguments for the call [default: {}]
  • -p, --permissions TEXT: File path to a token definition, if not specified default agent permissions will be used
  • --key TEXT: an api key to sign the token with
  • --help: Show this message and exit.

meshagent

Manage room-scoped secrets and OAuth flows Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • oauth: Request an OAuth token from another…
  • request: Request a secret from another participant.
  • get: Fetch a stored secret by ID.
  • exists: Check whether a stored secret exists by ID.
  • set: Store a secret by ID.
  • list: List secrets in the room.
  • delete: Delete a secret by ID.

meshagent oauth

Request an OAuth token from another participant. Usage:
$ meshagent   oauth [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --from-participant-id TEXT: Participant ID to request the token from [required]
  • --client-id TEXT: OAuth client ID [required]
  • --authorization-endpoint TEXT: OAuth authorization endpoint URL [required]
  • --token-endpoint TEXT: OAuth token endpoint URL [required]
  • --scopes TEXT: Comma-separated OAuth scopes
  • --client-secret TEXT: OAuth client secret (if required) [required]
  • --redirect-uri TEXT: Redirect URI for the OAuth flow [required]
  • --pkce / --no-pkce: Use PKCE (recommended) [default: pkce]
  • --help: Show this message and exit.

meshagent request

Request a secret from another participant. Usage:
$ meshagent   request [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --from-participant-id TEXT: Participant ID to request the secret from [required]
  • --url TEXT: Secret URL identifier [required]
  • --type TEXT: Secret type [default: application/octet-stream]
  • --delegate-to TEXT: Delegate secret to this participant name
  • --timeout INTEGER: Timeout in seconds [default: 300]
  • -o, --out TEXT: Output file path, or ’-’ for stdout [default: -]
  • --help: Show this message and exit.

meshagent get

Fetch a stored secret by ID. Usage:
$ meshagent   get [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --id TEXT: Secret ID [required]
  • --delegated-to TEXT: Fetch a secret delegated to this participant name
  • -o, --out TEXT: Output file path, or ’-’ for stdout [default: -]
  • --help: Show this message and exit.

meshagent exists

Check whether a stored secret exists by ID. Usage:
$ meshagent   exists [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --id TEXT: Secret ID [required]
  • --delegated-to TEXT: Check a secret delegated to this participant name
  • --for-identity TEXT: Check a secret for a specific identity
  • --help: Show this message and exit.

meshagent set

Store a secret by ID. Usage:
$ meshagent   set [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --id TEXT: Secret ID [required]
  • --type TEXT: Secret type
  • --name TEXT: Optional secret name
  • --delegated-to TEXT: Store a secret delegated to this participant name
  • --for-identity TEXT: Store a secret for a specific identity
  • -i, --in TEXT: Input file path, or ’-’ for stdin
  • --text TEXT: Provide secret as UTF-8 text
  • --base64 TEXT: Provide secret as base64-encoded data
  • --help: Show this message and exit.

meshagent list

List secrets in the room. Usage:
$ meshagent   list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --help: Show this message and exit.

meshagent delete

Delete a secret by ID. Usage:
$ meshagent   delete [OPTIONS] ID
Arguments:
  • ID: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --delegated-to TEXT: The value of the delegated_to field of the secret, must be specified if secret was delegated
  • --help: Show this message and exit.

meshagent

Manage room-scoped secrets and OAuth flows Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • oauth: Request an OAuth token from another…
  • request: Request a secret from another participant.
  • get: Fetch a stored secret by ID.
  • exists: Check whether a stored secret exists by ID.
  • set: Store a secret by ID.
  • list: List secrets in the room.
  • delete: Delete a secret by ID.

meshagent oauth

Request an OAuth token from another participant. Usage:
$ meshagent   oauth [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --from-participant-id TEXT: Participant ID to request the token from [required]
  • --client-id TEXT: OAuth client ID [required]
  • --authorization-endpoint TEXT: OAuth authorization endpoint URL [required]
  • --token-endpoint TEXT: OAuth token endpoint URL [required]
  • --scopes TEXT: Comma-separated OAuth scopes
  • --client-secret TEXT: OAuth client secret (if required) [required]
  • --redirect-uri TEXT: Redirect URI for the OAuth flow [required]
  • --pkce / --no-pkce: Use PKCE (recommended) [default: pkce]
  • --help: Show this message and exit.

meshagent request

Request a secret from another participant. Usage:
$ meshagent   request [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --from-participant-id TEXT: Participant ID to request the secret from [required]
  • --url TEXT: Secret URL identifier [required]
  • --type TEXT: Secret type [default: application/octet-stream]
  • --delegate-to TEXT: Delegate secret to this participant name
  • --timeout INTEGER: Timeout in seconds [default: 300]
  • -o, --out TEXT: Output file path, or ’-’ for stdout [default: -]
  • --help: Show this message and exit.

meshagent get

Fetch a stored secret by ID. Usage:
$ meshagent   get [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --id TEXT: Secret ID [required]
  • --delegated-to TEXT: Fetch a secret delegated to this participant name
  • -o, --out TEXT: Output file path, or ’-’ for stdout [default: -]
  • --help: Show this message and exit.

meshagent exists

Check whether a stored secret exists by ID. Usage:
$ meshagent   exists [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --id TEXT: Secret ID [required]
  • --delegated-to TEXT: Check a secret delegated to this participant name
  • --for-identity TEXT: Check a secret for a specific identity
  • --help: Show this message and exit.

meshagent set

Store a secret by ID. Usage:
$ meshagent   set [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --id TEXT: Secret ID [required]
  • --type TEXT: Secret type
  • --name TEXT: Optional secret name
  • --delegated-to TEXT: Store a secret delegated to this participant name
  • --for-identity TEXT: Store a secret for a specific identity
  • -i, --in TEXT: Input file path, or ’-’ for stdin
  • --text TEXT: Provide secret as UTF-8 text
  • --base64 TEXT: Provide secret as base64-encoded data
  • --help: Show this message and exit.

meshagent list

List secrets in the room. Usage:
$ meshagent   list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --help: Show this message and exit.

meshagent delete

Delete a secret by ID. Usage:
$ meshagent   delete [OPTIONS] ID
Arguments:
  • ID: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --delegated-to TEXT: The value of the delegated_to field of the secret, must be specified if secret was delegated
  • --help: Show this message and exit.

meshagent

Use queues in a room Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • list: List queues in a room.
  • send: Send a JSON message to a room queue.
  • send-mail: Create an email message and send it to a…
  • receive: Receive a message from a room queue.
  • size: Show the current size of a room queue.

meshagent list

List queues in a room. Usage:
$ meshagent   list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -o, --output TEXT: output format [default: table]
  • --help: Show this message and exit.

meshagent send

Send a JSON message to a room queue. Usage:
$ meshagent   send [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --queue TEXT: Queue name [required]
  • --json TEXT: a JSON message to send to the queue [required]
  • -f, --file TEXT: File path to a JSON file
  • --help: Show this message and exit.

meshagent send-mail

Create an email message and send it to a room queue. Usage:
$ meshagent   send-mail [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --queue TEXT: Queue name [required]
  • --subject TEXT: Email subject [required]
  • --body TEXT: Email body
  • --from TEXT: Sender email address [required]
  • --attachment TEXT: Attachment file path. May be provided multiple times.
  • --help: Show this message and exit.

meshagent receive

Receive a message from a room queue. Usage:
$ meshagent   receive [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --queue TEXT: Queue name [required]
  • --help: Show this message and exit.

meshagent size

Show the current size of a room queue. Usage:
$ meshagent   size [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --queue TEXT: Queue name [required]
  • --help: Show this message and exit.

meshagent

Send and receive messages in a room Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • list: List messaging-enabled participants
  • send: Send a direct message to a participant
  • broadcast: Broadcast a message to all participants

meshagent list

List messaging-enabled participants Usage:
$ meshagent   list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --help: Show this message and exit.

meshagent send

Send a direct message to a participant Usage:
$ meshagent   send [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --to-participant-id TEXT: Participant ID to send a message to [required]
  • --type TEXT: type of the message to send [required]
  • --data TEXT: JSON message to send [required]
  • --help: Show this message and exit.

meshagent broadcast

Broadcast a message to all participants Usage:
$ meshagent   broadcast [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --data TEXT: JSON message to broadcast [required]
  • --help: Show this message and exit.

meshagent

Manage storage for a room Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • exists: Check whether a path exists in room storage.
  • cp: Copy files between local paths and room…
  • show: Print file contents from local disk or…
  • rm: Remove files or directories from local…
  • ls: List files and directories locally or in…

meshagent exists

Check whether a path exists in room storage. Usage:
$ meshagent   exists [OPTIONS] PATH
Arguments:
  • PATH: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --help: Show this message and exit.

meshagent cp

Copy files between local paths and room storage. Usage:
$ meshagent   cp [OPTIONS] SOURCE_PATH DEST_PATH
Arguments:
  • SOURCE_PATH: [required]
  • DEST_PATH: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --help: Show this message and exit.

meshagent show

Print file contents from local disk or room storage. Usage:
$ meshagent   show [OPTIONS] PATH
Arguments:
  • PATH: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --encoding TEXT: Text encoding [default: utf-8]
  • --help: Show this message and exit.

meshagent rm

Remove files or directories from local disk or room storage. Usage:
$ meshagent   rm [OPTIONS] PATH
Arguments:
  • PATH: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -r: Remove directories/folders recursively
  • --help: Show this message and exit.

meshagent ls

List files and directories locally or in room storage. Usage:
$ meshagent   ls [OPTIONS] PATH
Arguments:
  • PATH: Path to list (local or room://…) [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -r: List subfolders/files recursively
  • --help: Show this message and exit.

meshagent

Manage services inside a room Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • list: List services running in a room
  • restart: Restart a running room service by stopping…

meshagent list

List services running in a room Usage:
$ meshagent   list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -o, --output TEXT: output format [default: table]
  • --help: Show this message and exit.

meshagent restart

Restart a running room service by stopping its current container. Usage:
$ meshagent   restart [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --id TEXT: Service ID to restart
  • --name TEXT: Service name to restart
  • --help: Show this message and exit.

meshagent

Manage services inside a room Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • list: List services running in a room
  • restart: Restart a running room service by stopping…

meshagent list

List services running in a room Usage:
$ meshagent   list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -o, --output TEXT: output format [default: table]
  • --help: Show this message and exit.

meshagent restart

Restart a running room service by stopping its current container. Usage:
$ meshagent   restart [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --id TEXT: Service ID to restart
  • --name TEXT: Service name to restart
  • --help: Show this message and exit.

meshagent watch

Stream developer logs from a room Usage:
$ meshagent  watch [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --format [plain|json]: Output format [default: plain]
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.

meshagent

Manage database tables in a room Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • table: List database tables in a room.
  • tables: List database tables in a room.
  • inspect: Inspect a table schema in a room database.
  • install: Install required tables from a…
  • create: Create a room database table with optional…
  • drop: Drop a room database table.
  • add-columns: Add columns to a room database table.
  • drop-columns: Drop columns from a room database table.
  • insert: Insert records into a room database table.
  • merge: Upsert records into a room database table.
  • update: Update rows in a room database table.
  • delete: Delete rows from a room database table.
  • search: Search rows in a room database table.
  • sql: Execute SQL against room database tables.
  • optimize: Optimize a room database table.
  • version: List versions for a room database table.
  • versions: List versions for a room database table.
  • restore: Restore a room database table to a…
  • index: List indexes on a room database table.
  • indexes: List indexes on a room database table.
  • index-create: Create an index on a room database table.
  • index-drop: Drop an index from a room database table.
  • branch: Manage database branches in a room namespace.

meshagent table

List database tables in a room. Usage:
$ meshagent   table [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --help: Show this message and exit.

meshagent tables

List database tables in a room. Usage:
$ meshagent   tables [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --help: Show this message and exit.

meshagent inspect

Inspect a table schema in a room database. Usage:
$ meshagent   inspect [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • -v, --version INTEGER: Historical table version to read (defaults to latest on the branch)
  • --json: Output raw schema JSON
  • --help: Show this message and exit.

meshagent install

Install required tables from a requirements JSON file. Usage:
$ meshagent   install [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --file TEXT: Path to requirements JSON file
  • --help: Show this message and exit.

meshagent create

Create a room database table with optional schema and seed data. Usage:
$ meshagent   create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • --mode TEXT: create | overwrite | create_if_not_exists [default: create]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • -c, --columns TEXT: Comma-separated column definitions. Example: “names vector(20) null, tags list(text), meta struct(owner text, score float)”. Allowed types: int, bool, date, timestamp, float, text, json, uuid, binary, vector, list, struct. Vector syntax: vector(size[, element_type]). List syntax: list(element_type). Struct syntax: struct(field_name type[, …]).
  • --schema-json TEXT: Schema JSON as a string
  • --schema-file TEXT: Path to schema JSON file
  • --data-json TEXT: Initial rows (JSON list)
  • --data-file TEXT: Path to JSON file with initial rows
  • --help: Show this message and exit.

meshagent drop

Drop a room database table. Usage:
$ meshagent   drop [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --ignore-missing: Ignore missing table
  • --help: Show this message and exit.

meshagent add-columns

Add columns to a room database table. Usage:
$ meshagent   add-columns [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • -c, --columns TEXT: Comma-separated column definitions. Example: “names vector(20) null, tags list(text), meta struct(owner text, score float)”. Allowed types: int, bool, date, timestamp, float, text, json, uuid, binary, vector, list, struct. Vector syntax: vector(size[, element_type]). List syntax: list(element_type). Struct syntax: struct(field_name type[, …]).
  • --columns-json TEXT: JSON object of new columns. Supports DataType JSON including list/struct (e.g. ’{“meta”:{“type”:“struct”,“fields”:{“owner”:{“type”:“text”}}}}’).
  • --help: Show this message and exit.

meshagent drop-columns

Drop columns from a room database table. Usage:
$ meshagent   drop-columns [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • -c, --column TEXT: Column to drop (repeatable)
  • --help: Show this message and exit.

meshagent insert

Insert records into a room database table. Usage:
$ meshagent   insert [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --json TEXT: JSON list of records
  • -f, --file TEXT: Path to JSON file (list of records)
  • --help: Show this message and exit.

meshagent merge

Upsert records into a room database table. Usage:
$ meshagent   merge [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • --on TEXT: Column to match for upsert [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --json TEXT: JSON records (list)
  • -f, --file TEXT: Path to JSON file (list)
  • --help: Show this message and exit.

meshagent update

Update rows in a room database table. Usage:
$ meshagent   update [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • --where TEXT: SQL WHERE clause, e.g. “id = 1” [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --values-json TEXT: JSON object of update values; use {“column”:{“expression”:”…”}} for expressions [required]
  • --help: Show this message and exit.

meshagent delete

Delete rows from a room database table. Usage:
$ meshagent   delete [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • --where TEXT: SQL WHERE clause [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --help: Show this message and exit.
Search rows in a room database table. Usage:
$ meshagent   search [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • -v, --version INTEGER: Historical table version to read (defaults to latest on the branch)
  • --text TEXT: Full-text query
  • --vector-json TEXT: Vector JSON array
  • --where TEXT: SQL WHERE clause
  • --where-json TEXT: JSON object converted to equality ANDs
  • --select TEXT: Columns to select (repeatable)
  • --limit INTEGER: Max rows to return
  • --offset INTEGER: Rows to skip
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent sql

Execute SQL against room database tables. Usage:
$ meshagent   sql [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -q, --query TEXT: SQL query to execute [required]
  • -t, --table TEXT: Table name to register in SQL context (repeatable)
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --tables-json TEXT: JSON array of table refs (e.g. ’[{“name”:“users”,“alias”:“u”,“namespace”:[“prod”]}]’)
  • --tables-file TEXT: Path/URL to JSON array of table refs (same format as —tables-json)
  • --params-json TEXT: JSON object of SQL parameters for DataFusion param binding
  • --params-file TEXT: Path/URL to JSON object of SQL parameters
  • --branch TEXT: Database branch name (defaults to main)
  • -v, --version INTEGER: Historical table version to read (defaults to latest on the branch)
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent optimize

Optimize a room database table. Usage:
$ meshagent   optimize [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --help: Show this message and exit.

meshagent version

List versions for a room database table. Usage:
$ meshagent   version [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent versions

List versions for a room database table. Usage:
$ meshagent   versions [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent restore

Restore a room database table to a specific version. Usage:
$ meshagent   restore [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -v, --version INTEGER: Table version [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --help: Show this message and exit.

meshagent index

List indexes on a room database table. Usage:
$ meshagent   index [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • -v, --version INTEGER: Historical table version to read (defaults to latest on the branch)
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent indexes

List indexes on a room database table. Usage:
$ meshagent   indexes [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • -v, --version INTEGER: Historical table version to read (defaults to latest on the branch)
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent index-create

Create an index on a room database table. Usage:
$ meshagent   index-create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • -c, --column TEXT: Column name [required]
  • --kind TEXT: vector | scalar | fts [default: scalar]
  • --replace / --no-replace: Replace existing index if it already exists
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --help: Show this message and exit.

meshagent index-drop

Drop an index from a room database table. Usage:
$ meshagent   index-drop [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -t, --table TEXT: Table name [required]
  • --name TEXT: Index name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --branch TEXT: Database branch name (defaults to main)
  • --help: Show this message and exit.

meshagent branch

Manage database branches in a room namespace. Usage:
$ meshagent   branch [OPTIONS] COMMAND [ARGS]...
Options:
  • --help: Show this message and exit.
Commands:
  • list: List database branches in a room namespace.
  • create: Create a database branch.
  • delete: Delete a database branch.
meshagent branch list
List database branches in a room namespace. Usage:
$ meshagent   branch list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.
meshagent branch create
Create a database branch. Usage:
$ meshagent   branch create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --branch TEXT: New branch name [required]
  • --from-branch TEXT: Source branch to branch from
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --help: Show this message and exit.
meshagent branch delete
Delete a database branch. Usage:
$ meshagent   branch delete [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --branch TEXT: Branch name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --help: Show this message and exit.

meshagent

Manage room memories Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • list: List memories in a room namespace.
  • create: Create a room memory store.
  • drop: Drop a room memory store.
  • inspect: Inspect metadata and datasets for a memory.
  • query: Run a SQL-like query against memory datasets.
  • upsert-table: Upsert records from JSON into memory tables.
  • upsert-nodes: Upsert entity nodes into memory.
  • upsert-relationships: Upsert relationship edges into memory.
  • import: Import entities and relationships from a…
  • ingest-text: Extract memory from input text.
  • ingest-image: Extract memory from an image.
  • ingest-file: Extract memory from local file/text content.
  • ingest-from-table: Extract memory from table rows.
  • ingest-from-storage: Extract memory from room storage paths.
  • recall: Recall entities and relationships from…
  • delete-entities: Delete entities (and related edges) from…
  • delete-relationships: Delete relationship edges from memory.
  • optimize: Optimize memory datasets.

meshagent list

List memories in a room namespace. Usage:
$ meshagent   list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent create

Create a room memory store. Usage:
$ meshagent   create [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --overwrite: Overwrite existing memory
  • --help: Show this message and exit.

meshagent drop

Drop a room memory store. Usage:
$ meshagent   drop [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --ignore-missing: Ignore missing memory
  • --help: Show this message and exit.

meshagent inspect

Inspect metadata and datasets for a memory. Usage:
$ meshagent   inspect [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent query

Run a SQL-like query against memory datasets. Usage:
$ meshagent   query [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -s, --statement TEXT: Statement, e.g. “MATCH (e:Entity) RETURN e.name LIMIT 10” [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent upsert-table

Upsert records from JSON into memory tables. Usage:
$ meshagent   upsert-table [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -t, --table TEXT: Table name [required]
  • --records-json TEXT: JSON array of records
  • --records-file TEXT: Path to JSON file with records
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --merge / --no-merge: Merge with existing records [default: merge]
  • --help: Show this message and exit.

meshagent upsert-nodes

Upsert entity nodes into memory. Usage:
$ meshagent   upsert-nodes [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • --records-json TEXT: JSON array of MemoryEntityRecord objects
  • --records-file TEXT: Path to JSON file with entity records
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --merge / --no-merge: Merge with existing nodes [default: merge]
  • --help: Show this message and exit.

meshagent upsert-relationships

Upsert relationship edges into memory. Usage:
$ meshagent   upsert-relationships [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • --records-json TEXT: JSON array of MemoryRelationshipRecord objects
  • --records-file TEXT: Path to JSON file with relationship records
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --merge / --no-merge: Merge with existing relationships [default: merge]
  • --help: Show this message and exit.

meshagent import

Import entities and relationships from a FalkorDB dump.rdb file. Usage:
$ meshagent   import [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -f, --rdb-file PATH: Path to FalkorDB dump.rdb file [required]
  • --graph-name TEXT: FalkorDB graph key name. Auto-detected when unambiguous.
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --merge / --no-merge: Merge with existing records [default: merge]
  • --batch-size INTEGER RANGE: Rows per GRAPH.QUERY batch while importing [default: 250; x>=1]
  • --docker-image TEXT: Docker image to use for temporary FalkorDB container [default: falkordb/falkordb:latest]
  • --startup-timeout-seconds FLOAT RANGE: Max seconds to wait for FalkorDB startup [default: 30.0; x>=1.0]
  • --create-memory / --no-create-memory: Create the target memory when missing [default: create-memory]
  • --help: Show this message and exit.

meshagent ingest-text

Extract memory from input text. Usage:
$ meshagent   ingest-text [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • --text TEXT: Text content to ingest
  • -f, --file TEXT: Path to UTF-8 text file
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --strategy [heuristic|llm]: Ingest strategy: heuristic or llm [default: heuristic]
  • --llm-model TEXT: Model name for llm strategy
  • --llm-temperature FLOAT: Temperature for llm strategy
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent ingest-image

Extract memory from an image. Usage:
$ meshagent   ingest-image [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -f, --file TEXT: Path to image file
  • --caption TEXT: Optional image caption
  • --mime-type TEXT: Image mime type
  • --source TEXT: Source identifier/path
  • --annotations-json TEXT: Optional JSON map of string annotations, e.g. {“origin”:“camera”}
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --strategy [heuristic|llm]: Ingest strategy: heuristic or llm [default: heuristic]
  • --llm-model TEXT: Model name for llm strategy
  • --llm-temperature FLOAT: Temperature for llm strategy
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent ingest-file

Extract memory from local file/text content. Usage:
$ meshagent   ingest-file [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • --path TEXT: File path available to the room server
  • --text TEXT: Inline text content
  • --text-file TEXT: Path to local UTF-8 text file
  • --mime-type TEXT: Optional mime type
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --strategy [heuristic|llm]: Ingest strategy: heuristic or llm [default: heuristic]
  • --llm-model TEXT: Model name for llm strategy
  • --llm-temperature FLOAT: Temperature for llm strategy
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent ingest-from-table

Extract memory from table rows. Usage:
$ meshagent   ingest-from-table [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -t, --table TEXT: Source table name [required]
  • --text-column TEXT: Source text columns (repeatable)
  • --table-namespace TEXT: Namespace path segments for the source table (repeatable)
  • --limit INTEGER: Maximum source rows
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --strategy [heuristic|llm]: Ingest strategy: heuristic or llm [default: heuristic]
  • --llm-model TEXT: Model name for llm strategy
  • --llm-temperature FLOAT: Temperature for llm strategy
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent ingest-from-storage

Extract memory from room storage paths. Usage:
$ meshagent   ingest-from-storage [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -p, --path TEXT: Room storage path to ingest (repeatable) [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --strategy [heuristic|llm]: Ingest strategy: heuristic or llm [default: heuristic]
  • --llm-model TEXT: Model name for llm strategy
  • --llm-temperature FLOAT: Temperature for llm strategy
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent recall

Recall entities and relationships from memory. Usage:
$ meshagent   recall [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -q, --query TEXT: Recall query text [required]
  • --limit INTEGER: Max entities to return [default: 5]
  • --include-relationships / --no-include-relationships: Include related edges for recalled entities [default: include-relationships]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent delete-entities

Delete entities (and related edges) from memory. Usage:
$ meshagent   delete-entities [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -e, --entity-id TEXT: Entity ID to delete (repeatable) [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent delete-relationships

Delete relationship edges from memory. Usage:
$ meshagent   delete-relationships [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • --records-json TEXT: JSON array of MemoryRelationshipSelector objects
  • --records-file TEXT: Path to JSON file with relationship selectors
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent optimize

Optimize memory datasets. Usage:
$ meshagent   optimize [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -m, --name TEXT: Memory name [required]
  • -n, --namespace TEXT: Namespace path segments (repeatable). Example: -n prod -n analytics
  • --compact / --no-compact: Compact dataset fragments [default: compact]
  • --cleanup / --no-cleanup: Cleanup old dataset versions [default: cleanup]
  • --pretty / --no-pretty: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent

Manage containers and images inside a room Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • list: List containers in a room.
  • stop: Stop a running container in a room.
  • log: Print container logs from a room.
  • logs: Print container logs from a room.
  • exec: Execute a command inside a running container.
  • run: Run a container inside a room.
  • “: Image operations
  • “: Image operations

meshagent list

List containers in a room. Usage:
$ meshagent   list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -a, --all: Include exited containers in the listing.
  • --output TEXT: json | table [default: json]
  • --help: Show this message and exit.

meshagent stop

Stop a running container in a room. Usage:
$ meshagent   stop [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --id TEXT: Container ID [required]
  • --help: Show this message and exit.

meshagent log

Print container logs from a room. Usage:
$ meshagent   log [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --id TEXT: Container ID [required]
  • --follow / --no-follow: Stream logs [default: no-follow]
  • --help: Show this message and exit.

meshagent logs

Print container logs from a room. Usage:
$ meshagent   logs [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --id TEXT: Container ID [required]
  • --follow / --no-follow: Stream logs [default: no-follow]
  • --help: Show this message and exit.

meshagent exec

Execute a command inside a running container. Usage:
$ meshagent   exec [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --container-id TEXT: container id [required]
  • --command TEXT: Command to execute in the container (quoted string)
  • --help: Show this message and exit.

meshagent run

Run a container inside a room. Usage:
$ meshagent   run [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --image TEXT: Image to run [required]
  • --command TEXT: Command to execute in the container (quoted string)
  • --working-dir TEXT: Working directory inside the container (must be an absolute path)
  • -e, --env TEXT: KEY=VALUE
  • -p, --port TEXT: CONTAINER:HOST
  • --cred TEXT: Docker creds (username,password) or (registry,username,password)
  • --mount-path TEXT: Room storage path to mount into the container
  • --mount-subpath TEXT: Subpath within --mount-path to mount
  • --participant-name TEXT: Participant name to associate with the run
  • --role TEXT: Role to run the container as [default: user]
  • --container-name TEXT: Optional container name
  • --help: Show this message and exit.

meshagent

Image operations Usage:
$ meshagent    [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • list: List container images available in a room.
  • delete: Delete a container image from a room.
  • pull: Pull a container image into a room.
  • push: Push a container image from a room.
  • load: Load an OCI image archive from room…
  • save: Save an OCI image archive from a room.
meshagent list
List container images available in a room. Usage:
$ meshagent    list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --help: Show this message and exit.
meshagent delete
Delete a container image from a room. Usage:
$ meshagent    delete [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --image TEXT: Image ref/tag to delete [required]
  • --help: Show this message and exit.
meshagent pull
Pull a container image into a room. Usage:
$ meshagent    pull [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --tag TEXT: Image tag/ref to pull [required]
  • --cred TEXT: Docker creds (username,password) or (registry,username,password)
  • --help: Show this message and exit.
meshagent push
Push a container image from a room. Usage:
$ meshagent    push [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --tag TEXT: Image tag/ref to push [required]
  • --private / --public: Whether the push container is private to the participant [default: public]
  • --cred TEXT: Docker creds (username,password) or (registry,username,password)
  • --help: Show this message and exit.
meshagent load
Load an OCI image archive from room storage into a room. Usage:
$ meshagent    load [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -i, --archive-path, --image TEXT: Absolute room storage path to the OCI image archive file [required]
  • --help: Show this message and exit.
meshagent save
Save an OCI image archive from a room. Usage:
$ meshagent    save [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --tag TEXT: Image tag/ref to save [required]
  • --archive-path TEXT: Path to write OCI archive inside one of the mounted paths (absolute path) [required]
  • --mount-room-path TEXT: Room storage mount ‘<source>:<mount>[:ro|rw]’. Example ‘/images:/workspace’
  • --mount-project-path TEXT: Project storage mount ‘<source>:<mount>[:ro|rw]’. Example ‘/shared:/project:ro’
  • --mount-image TEXT: Image mount ‘<image>=<mount>[:ro|rw]’. Example ‘alpine:latest=/toolchain:ro’
  • --private / --public: Whether the save container is private to the participant [default: public]
  • --help: Show this message and exit.

meshagent

Image operations Usage:
$ meshagent    [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • list: List container images available in a room.
  • delete: Delete a container image from a room.
  • pull: Pull a container image into a room.
  • push: Push a container image from a room.
  • load: Load an OCI image archive from room…
  • save: Save an OCI image archive from a room.
meshagent list
List container images available in a room. Usage:
$ meshagent    list [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --help: Show this message and exit.
meshagent delete
Delete a container image from a room. Usage:
$ meshagent    delete [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --image TEXT: Image ref/tag to delete [required]
  • --help: Show this message and exit.
meshagent pull
Pull a container image into a room. Usage:
$ meshagent    pull [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --tag TEXT: Image tag/ref to pull [required]
  • --cred TEXT: Docker creds (username,password) or (registry,username,password)
  • --help: Show this message and exit.
meshagent push
Push a container image from a room. Usage:
$ meshagent    push [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --tag TEXT: Image tag/ref to push [required]
  • --private / --public: Whether the push container is private to the participant [default: public]
  • --cred TEXT: Docker creds (username,password) or (registry,username,password)
  • --help: Show this message and exit.
meshagent load
Load an OCI image archive from room storage into a room. Usage:
$ meshagent    load [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -i, --archive-path, --image TEXT: Absolute room storage path to the OCI image archive file [required]
  • --help: Show this message and exit.
meshagent save
Save an OCI image archive from a room. Usage:
$ meshagent    save [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --tag TEXT: Image tag/ref to save [required]
  • --archive-path TEXT: Path to write OCI archive inside one of the mounted paths (absolute path) [required]
  • --mount-room-path TEXT: Room storage mount ‘<source>:<mount>[:ro|rw]’. Example ‘/images:/workspace’
  • --mount-project-path TEXT: Project storage mount ‘<source>:<mount>[:ro|rw]’. Example ‘/shared:/project:ro’
  • --mount-image TEXT: Image mount ‘<image>=<mount>[:ro|rw]’. Example ‘alpine:latest=/toolchain:ro’
  • --private / --public: Whether the save container is private to the participant [default: public]
  • --help: Show this message and exit.

meshagent

Inspect and update mesh documents in a room Usage:
$ meshagent   [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • show: Print the full document JSON
  • grep: Search the document for matching content
  • inspect: Print the document schema JSON
  • create: Create a new document at a path
  • update: Apply a JSON patch to a document
  • threads: Import Anthropic Claude GDPR conversations…

meshagent show

Print the full document JSON Usage:
$ meshagent   show [OPTIONS] PATH
Arguments:
  • PATH: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --include-ids: Include $id attributes in output
  • --pretty / --compact: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent grep

Search the document for matching content Usage:
$ meshagent   grep [OPTIONS] PATH PATTERN
Arguments:
  • PATH: [required]
  • PATTERN: Regex pattern to match [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --ignore-case: Ignore case
  • --before INTEGER RANGE: Include siblings before [default: 0; x>=0]
  • --after INTEGER RANGE: Include siblings after [default: 0; x>=0]
  • --include-ids: Include $id attributes in output
  • --pretty / --compact: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent inspect

Print the document schema JSON Usage:
$ meshagent   inspect [OPTIONS] PATH
Arguments:
  • PATH: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --pretty / --compact: Pretty-print JSON [default: pretty]
  • --help: Show this message and exit.

meshagent create

Create a new document at a path Usage:
$ meshagent   create [OPTIONS] PATH
Arguments:
  • PATH: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --schema PATH: Schema JSON file [required]
  • --json TEXT: Initial JSON payload
  • --json-file PATH: Path to initial JSON payload
  • --help: Show this message and exit.

meshagent update

Apply a JSON patch to a document Usage:
$ meshagent   update [OPTIONS] PATH
Arguments:
  • PATH: [required]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • --patch TEXT: JSON patch array
  • --patch-file PATH: Path to JSON patch array
  • --help: Show this message and exit.

meshagent threads

Import Anthropic Claude GDPR conversations into room thread documents. Usage:
$ meshagent   threads [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --room TEXT: Room name [default: (dynamic)]
  • -f, --file PATH: Path to Claude GDPR conversations.json [required]
  • --thread-dir TEXT: Directory where imported .thread files will be stored [default: .threads/anthropic]
  • --overwrite: Overwrite existing imported thread files
  • --limit INTEGER RANGE: Maximum number of conversations to import [x>=1]
  • --user-name, --human-name TEXT: Author name used for user/human messages [default: human]
  • --assistant-name TEXT: Author name used for assistant messages [default: assistant]
  • --include-empty-messages: Include messages that normalize to empty text
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.

meshagent connect

Connect to a room and run a local command with MESHAGENT_API_URL, MESHAGENT_PROJECT_ID, MESHAGENT_TOKEN, OPENAI_API_KEY, ANTHROPIC_API_KEY, and MESHAGENT_ROOM set. Use — before the local command. Usage:
$ meshagent  connect [OPTIONS] [COMMAND]...
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used.
  • --room TEXT: Room name
  • -e, --env TEXT: Set environment variable as KEY=VALUE
  • --env-secret TEXT: Set environment variable from a room secret as NAME=SECRET_ID
  • --identity TEXT: Identity name to use for the connected token, —meshagent-token, and —env-secret. Required with —meshagent-token and —env-secret. When set, room connect mints a participant token locally.
  • --meshagent-token TEXT: Inject MESHAGENT_TOKEN using userDefault, agentDefault, full, or a JSON ApiScope object.
  • --help: Show this message and exit.

meshagent

Local LLM proxy utilities Usage:
$ meshagent  [OPTIONS] COMMAND [ARGS]...
Options:
  • --install-completion: Install completion for the current shell.
  • --show-completion: Show completion for the current shell, to copy it or customize the installation.
  • --help: Show this message and exit.
Commands:
  • proxy: Expose a local MeshAgent-authenticated LLM…

meshagent proxy

Expose a local MeshAgent-authenticated LLM proxy. Usage:
$ meshagent  proxy [OPTIONS]
Options:
  • --project-id TEXT: A MeshAgent project id. If empty, the activated project will be used. [default: (dynamic)]
  • --host TEXT: Local host to bind the proxy to. [default: 127.0.0.1]
  • --port INTEGER: Local port to bind the proxy to. [default: 8766]
  • --bearer TEXT: Explicit local bearer token. If omitted, the stored token is reused or generated on first run.
  • --token-from-env TEXT: Name of environment variable containing a MeshAgent token to forward upstream.
  • --insecure: Disable local bearer-token enforcement.
  • --tui / --no-tui: Show the live usage dashboard when attached to a TTY. [default: tui]
  • --help: Show this message and exit.