Meshagent expands on traditional agent frameworks by focusing on inter-framework interoperability, rich human-in-the-loop workflows, and seamless multi-device reach. You can use Meshagent’s Agent framework to build new agents or layer them on top of your existing agents so that you can continue to build agent logic with familiar frameworks—OpenAI Agents SDK, Semantic Kernel, CrewAI, or anything else—while letting Meshagent handle the parts they typically leave to you:

  • Room-based connectivity. Agents, tools, and user interfaces join the same room over a lightweight WebSocket mesh. This lets Python, Dart, JavaScript, or .NET components talk to one another as peers instead of forcing every call through a single back-end service.
  • Tool abstraction across client and server. Any capability—opening a local file, showing a toast on a mobile device, invoking an internal REST API—becomes a Meshagent tool. Tools can live in the user’s device, on your cloud server, or both, yet they’re invoked through the same call pattern from the agent’s perspective.
  • First-class observability and cost tracking. Every tool call automatically records who invoked it, latency, result size, and cost metadata, feeding dashboards and billing pipelines without extra code.
  • Plug-and-play UI components. Meshagent Studio and the React / Flutter UI kits render agent interactions, streaming responses, and tool call progress out of the box, letting you drop high-quality UX into your own app.

​
Cross-Framework, Cross-Device Example

Suppose your agent is written in Python and hosted on a server, while your customer-facing app is a Flutter mobile client. By connecting both to the same Meshagent room:

  • The Flutter app registers UI-centric tools—ask_user, ask_user_file, show_toast.
  • The Python agent calls those tools exactly like any other function, even though they execute on the user’s phone.
  • Observability events stream back automatically, so you can audit how often dialogs appeared, how long file picks took, and what it cost.

No additional RPC plumbing, versioning, or security tunnel is required; the room’s mesh protocol handles transport, authentication, and fallback across networks.

​
Built-in Agent Templates

Meshagent ships template agents you can use as-is, customize, or wrap around agents you already have:

  • Chatbot – Streams tool calls and responses, persists every exchange as a MeshDocument, and renders natively in Studio.
  • Voice – Adds real-time speech I/O while retaining full tool access inside the room.
  • TaskRunner – Executes a single, explicit task when invoked via SDK or as a callable room tool.
  • Indexer – Watches incoming content, embeds it into the room’s vector store, and integrates with RagToolkit for retrieval-augmented generation.
  • Worker – Listens to the room’s queue and processes each message in turn—ideal for background jobs or long-running tasks.

Start with these templates in the meshagent-agents project on pypi or wrap your own agent class; either way you immediately gain Studio testing, UI integration, and observability without rewriting business logic.

​
Why Use Meshagent When You Already Have Another Framework?

Other frameworks excel at defining an agent’s reasoning loop, memory, or planner. Meshagent focuses on everything around that core:

  • Bridging languages and runtimes. A TypeScript UI, a Python agent, and a Go microservice can collaborate in a single room without bespoke adapters.
  • Interactive UX out of the box. Human approval steps, progress bars, and device-side actions are first-class citizens, not after-thought hooks.
  • Operational insights baked in. Tool metrics, latency histograms, and per-user cost attribution require no extra middleware.

Use Meshagent alone, or pair it with your preferred planner or memory framework.