​
Overview

The MeshAgent ChatBot lets you add a conversational (chat/text based) agent to any MeshAgent Room with just a few lines of code! In this quickstart we’ll build the agent in three phases:
  1. Basic ChatBot: A simple agent with a system prompt (rules)
  2. ChatBot with Built-in MeshAgent Tools: Extend our chat agent by adding MeshAgent’s prebuilt tools to interact with the user and write documents to the room.
  3. ChatBot with Built-in MeshAgent Tools and Custom Tools: Add our own tools to the agent for use-case specific tasks.
You’ll learn how to:
  • Build a chat based agent with MeshAgent
  • Connect the agent to a MeshAgent Room for live testing.
  • Deploy the agent as a MeshAgent Service.
  • Generate a shareable link so others can start chatting right away.

​
Prerequisites

Be sure you have created your MeshAgent account and project, set up and activated a virtual environment, and installed the MeshAgent Python SDK. s For help getting setup see the Getting Started Guide.

​
Connect to MeshAgent Project

meshagent setup

​
Chat with the built-in ChatBot (zero code)

Let’s bring a ready-made chatbot into a room and talk to it: 
meshagent chatbot join --room gettingstarted --agent-name chatagent --name chatagent
Running this command will:
  1. Create and open a room called gettingstarted inside your project
  2. Call the chatagent into the gettingstarted room
In a web browser, go to studio.meshagent.com and join the gettingstarted room. You will see the chatagent participant appear! Simply select the agent and begin typing to talk to it.

​
Phase 1: Building a Simple ChatBot

Now that we’ve seen the default chatbot in action, let’s create one from scratch. Create a main.py file and paste the starter code below for the basic ChatBot. To start, we can give the agent one rule / system instruction. We’ll build up this code over the course of this example.
Python
import os
import asyncio

from meshagent.api import RequiredToolkit
from meshagent.agents.chat import ChatBot
from meshagent.openai import OpenAIResponsesAdapter
from meshagent.api.services import ServiceHost
from meshagent.otel import otel_config

service = ServiceHost(
    port=int(os.getenv("MESHAGENT_PORT","7777"))
)

otel_config(service_name="my-service") # automatically enables telemetry data collection for your agents and tools 

@service.path("/chat")
class SimpleChatbot(ChatBot):
    def __init__(self):
        super().__init__(
            name="mychatbot",
            title="chatbot",
            description="a simple chatbot",
            rules=[
                "Always respond to the user first then include a fun fact at the end of your response."
            ],
            llm_adapter = OpenAIResponsesAdapter(),
        )

print(f"running on port {service.port}")
asyncio.run(service.run())

​
Running the Simple ChatBot in Test Mode:

Time to try it out! To run the agent you will need two tabs open in your terminal. You need to be in the appropriate directory and have your virtual environment activated in each tab. In the first tab run: 
python main.py
In the second tab run the call agent command to bring our agent into the room: 
meshagent call agent --url=http://localhost:7777/chat --room=gettingstarted --participant-name=chatagent
Note: This will bring in the agent named chatagent into the gettingstarted room and run it on port 7777 using the service path chat. If you want to rename the agent, room, port, or service path simply update the variables in the command. Now we can navigate to the MeshAgent Studio and we’ll see our agent, “mychatagent” show up under the messaging tab! We can chat back and forth with the agent, asking it questions and making sure that it responds with a fun fact like we told it to. We can also click on the menu inside the room and turn on the “Developer console” this will allow us to see live logs, traces, and metrics as we interact with the agent.

​
Phase 2: Adding Built-in MeshAgent Tools to our ChatBot

Next, let’s give our agent the ability to interact with the user, convert documents to markdown, and write documents to the room. We can do this by adding toolkits to our agent. Toolkits represent a group of tools that are used for a particular purpose. We’ll also add a few imports and update the chat agent’s rules so it knows how to interact with the available tools more efficiently.
Python
import os
import asyncio

from meshagent.api import RequiredToolkit, RequiredSchema
from meshagent.agents.chat import ChatBot
from meshagent.openai import OpenAIResponsesAdapter
from meshagent.api.services import ServiceHost
from meshagent.tools.document_tools import DocumentAuthoringToolkit, DocumentTypeAuthoringToolkit
from meshagent.agents.schemas.document import document_schema
from meshagent.otel import otel_config

service = ServiceHost(
    port=int(os.getenv("MESHAGENT_PORT","7777"))
)

otel_config(service_name="my-service") # automatically enables telemetry data collection for your agents and tools 

@service.path("/chat")
class SimpleChatbot(ChatBot):
    def __init__(self):
        super().__init__(
            name="mychatbot",
            title="chatbot",
            description="a simple chatbot",
            rules=[
                "Always respond to the user and include a fun fact at the end of your response.",
                "use the ask_user tool to pick the name of a document, pick a document name if the tool is not available.",
                "the document names MUST have the extension .document, automatically add the extension if it is not provided",
                "you MUST always write content to a document",
                "first open a document, then use tools to write the document content before closing the document",
                "before closing the document, ask the user if they would like any additional modifications to be made to the document, and if so, make them. continue to ask the user until they are happy with the contents. you are not finished until the user is happy.",
                "blob URLs MUST not be added to documents, they must be saved as files first",
            ],
            llm_adapter = OpenAIResponsesAdapter(),
            requires=[
                RequiredToolkit(
                    name="ui"
                ),
                RequiredSchema(
                    name="document"
                ),
                RequiredToolkit(
                    name="meshagent.markitdown", 
                    tools=["markitdown_from_file"]
                ),
            ],
            toolkits=[
                DocumentAuthoringToolkit(),
                DocumentTypeAuthoringToolkit(
                    schema=document_schema,
                    document_type="document"
                )
            ],
        )

print(f"running on port {service.port}")
asyncio.run(service.run())
We can test the agent using the same commands as we did with the simple chat agent! 
python main.py

meshagent call agent --url=http://localhost:7777/chat --room=gettingstarted --participant-name=chatagent

​
Phase 3: Adding Custom Tools to our ChatBot

Now let’s add a custom tool to our ChatBot! We’ll create a TaskTracker toolkit that allows the agent to write and read tasks to the Room database. To do this we will update the chat agent initialization to create a table for the tasks when the room starts up. We will create a tasks toolkit with two custom tools to WriteTask and GetTasks from the database. This is a simple example of adding tasks, to create a more useful task writer we’d want to add date information and other metadata to better track and filter tasks. This example is mainly to demonstrate writing to room storage and adding custom tools to our chat agent.
Python
import os
import asyncio
import uuid
from datetime import datetime, timezone, timedelta

from meshagent.api import RequiredToolkit, RequiredSchema
from meshagent.agents.chat import ChatBot
from meshagent.openai import OpenAIResponsesAdapter
from meshagent.api.services import ServiceHost
from meshagent.tools.document_tools import DocumentAuthoringToolkit, DocumentTypeAuthoringToolkit
from meshagent.agents.schemas.document import document_schema
from meshagent.api.room_server_client import TextDataType, TimestampDataType
from meshagent.api.messaging import TextResponse, JsonResponse
from meshagent.tools import Tool, Toolkit
from meshagent.otel import otel_config

service = ServiceHost(
    port=int(os.getenv("MESHAGENT_PORT","7777"))
)

otel_config(service_name="my-service") # automatically enables telemetry data collection for your agents and tools 

class WriteTask(Tool):
    def __init__(self):
        super().__init__(
            name="WriteTask",
            title="Add a task",
            description="A tool to add tasks to the database",
            input_schema={
                "type": "object",
                "additionalProperties" : False,
                "required": [
                    "taskdescription"
                    ],
                "properties": {
                    "taskdescription": {"type": "string"}
                    }
            }
        )

    async def execute(self, context, taskdescription: str):
        await context.room.database.insert(
            table="tasks",
            records=[{
                "task_id": str(uuid.uuid4()),
                "taskdescription": taskdescription
            }]
        )
        return TextResponse(text="Task added!")
    
class GetTasks(Tool):
    def __init__(self):
        super().__init__(
            name="GetTasks",
            title="List tasks",
            description="List tasks recorded today or this week",
            input_schema={
                "type": "object",
                "additionalProperties":False,
                "required": [],
                "properties": {}
            }
        )

    async def execute(self, context):
        return JsonResponse(json={"values": await context.room.database.search(table="tasks")})

@service.path("/chat")
class SimpleChatbot(ChatBot):
    def __init__(self):
        super().__init__(
            name="mychatbot",
            title="chatbot",
            description="a simple chatbot",
            rules=[
                "Always respond to the user and include a fun fact at the end of your response.",
                "use the ask_user tool to pick the name of a document, pick a document name if the tool is not available.",
                "the document names MUST have the extension .document, automatically add the extension if it is not provided",
                "you MUST always write content to a document",
                "first open a document, then use tools to write the document content before closing the document",
                "before closing the document, ask the user if they would like any additional modifications to be made to the document, and if so, make them. continue to ask the user until they are happy with the contents. you are not finished until the user is happy.",
                "blob URLs MUST not be added to documents, they must be saved as files first",
            ],
            llm_adapter = OpenAIResponsesAdapter(),
            requires=[
                RequiredToolkit(
                    name="ui"
                ),
                RequiredSchema(
                    name="document"
                ),
                RequiredToolkit(
                    name="meshagent.markitdown", 
                    tools=["markitdown_from_file"]
                ),
            ],
            toolkits=[
                DocumentAuthoringToolkit(),
                DocumentTypeAuthoringToolkit(
                    schema=document_schema,
                    document_type="document"
                ),
                Toolkit(name="tasktracker", tools=[WriteTask(), GetTasks()]) # Add our Custom Tools Here!
            ],
        )

    async def start(self, *, room):
        await super().start(room=room)
        # One tiny table:
        await room.database.create_table_with_schema(
            name="tasks",
            schema={
                "task_id": TextDataType(),
                "taskdescription": TextDataType()
            },
            mode="overwrite",
            data=None
        )

print(f"running on port {service.port}")
asyncio.run(service.run())
We can test the agent using the same commands as we did with the simple chat agent! And now when we go to the room we can ask the agent to add a task to our task database. 
python main.py

meshagent call agent --url=http://localhost:7777/chat --room=gettingstarted --participant-name=chatagent
Once we’re satisfied with how the agent is performing we can deploy and share it. Note: Building an agent will likely take multiple rounds of iterating through writing different versions of the system prompt and crafting the best tools for the agent.

​
Deploying and Running the Agent as a MeshAgent Service

​
Prerequisites:

To deploy the agent you will need to have docker setup and a container registry with your cloud provider (e.g. GCP, Azure, AWS). For this example we are using Azure Container Registry. These steps assume you have created a container registry in Azure, have a service principal setup, and have the appropriate permissions to access and push images to the container registry. You will need to create a new image pull secret so that MeshAgent can pull and run your container, the image pull secret requires the service principal ID and password. To save the image pull secret navigate to the MeshAgent Studio, click the Secrets tab, then click New Image Pull Secret, give a name to your secret and fill in the required information. Once you have the registry setup proceed with the following steps.

​
Step 1: Build and Push Your Container

  1. Create and activate a dedicated Buildx builder We recommend using zstd images to speed up image pulls. To enable building zstd images, run the following commands:
docker buildx create --name zstd-builder --driver docker-container
docker buildx use zstd-builder
  1. Log in to Azure, connect to your ACR instance, then build and push the docker container. To build this container, use docker buildx to make a linux/amd64 image and push it to your registry.
az login
az acr login --name myregistry
docker buildx build . --platform linux/amd64 --output=type=image,name=myregistry.azurecr.io/mychatagent:v1,oci-mediatypes=true,compression=zstd,compression-level=3,force-compression=true,push=true

​
Step 2: Create a Service in MeshAgent for each of your Agents

  1. Navigate to the Services tab and click the button to create a New Service and fill in the required information about the agent.
  2. Add the MESHAGENT_PORT as an environment variable, this needs to match the port that you register the service with.

​
Step 3: Try your agent!

Navigate to the Sessions tab in MeshAgent Studio and either join an existing room or create a new room by starting a session. You will then see the Chatbot Agent available in the room for you to interact with!
  1. Navigate to your Room, click the hamburger menu icon in the top left corner, next click “Share”
  2. Select the Room and Agent you’d like to share and click “Generate Link”
  3. Proudly share your Agent!