CopilotKit/open-multi-agent-canvas

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

What it solves

It provides a dynamic chat interface that allows users to manage and interact with multiple AI agents within a single conversation, simplifying complex tasks like travel planning and research.

How it works

Built with Next.js, LangGraph, and CopilotKit, the project implements a multi-agent canvas. It integrates with the Model Context Protocol (MCP) to connect to various servers—including local Python scripts via Standard IO or external servers via Server-Sent Events (SSE)—allowing agents to access external tools and data.

Who it’s for

Developers building AI applications that require coordination between multiple specialized agents or those wanting to integrate MCP-compatible servers into a chat interface.

Highlights

  • Multi-agent management in one conversation.
  • Support for Model Context Protocol (MCP) servers (Standard IO and SSE).
  • Integration with LangGraph and CopilotKit.
  • Pre-built examples for travel agents and AI researchers.

Related

  • Project
    Shy2593666979/AgentChat

    AgentChat is an open‑source, full‑stack conversational AI platform. It combines a Vue 3 front‑end with a FastAPI + LangChain back‑end to deliver LLM‑driven chat, multi‑agent collaboration, three‑tier memory (short‑term, summarised history, long‑term user prefs), RAG via vector stores, tool calling (including custom OpenAPI tools), and Model‑Context‑Protocol integration. Docker‑compose provides one‑click deployment; the project is MIT‑licensed.

  • Project
    bcurts/agentchattr

    agentchattr is a cross‑platform local chat server that lets you and multiple AI coding agents converse in real‑time. By @‑mentioning an agent in the web UI, the server injects a prompt into the agent’s terminal (via MCP), the agent reads the chat and replies automatically, enabling hands‑free coordination, multi‑agent workflows, jobs, rules, sessions, and a rich UI with channels, pins, decision cards, scheduling, voice typing, and more.

  • Project
    op7418/CodePilot

    A multi-model AI agent desktop client that unifies 17+ AI providers into one interface with persistent memory, remote control via messaging apps, and MCP support.

  • Project
    plurai-ai/intellagent

    A multi-agent framework that stress-tests conversational AI agents by simulating thousands of realistic edge-case interactions to uncover failure points and optimize performance.

  • Project
    Azure-Samples/azure-ai-travel-agents

    A modular reference application that uses multiple AI agents and the Model Context Protocol (MCP) to automate travel tasks like destination recommendation and itinerary planning.