OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

Open Multi Agent Canvas

Open Multi-Agent Canvas is an open-source web chat interface for managing multiple agents in one conversation. It includes an MCP agent that handles tasks through configurable MCP-compatible servers, and is built with Next.js, LangGraph and CopilotKit.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Open Multi Agent Canvas — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a task benefits from bringing multiple agents into one chat or connecting an agent to MCP servers. The repository also documents a developer setup path for its frontend and optional backend.

Who it is for

  • People coordinating several agents for research, travel planning or general-purpose tasks.
  • Developers exploring a chat interface connected to configurable MCP servers.

Documented uses

  • Manage multiple agents within one conversation.
  • Connect the included MCP agent to MCP-compatible servers.
  • Use an agent interface for research, travel planning and general-purpose tasks.
Before you choose

Requirements & limits

The README says Copilot Cloud and a CopilotKit API key are required to run the project. It documents pnpm for frontend setup. The optional MCP backend setup uses Poetry and requires OpenAI and LangSmith API keys.

  • The included MCP agent supports configurable server connections through Standard IO or SSE.
  • The README lists separate CoAgents travel and AI researcher examples; those agents live in separate repositories.
  • The project has been consolidated into the CopilotKit monorepo, which the README identifies as the location of the latest version.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the frontend

Install and start the documented Next.js frontend.

Before you start

  • pnpm
  • A Copilot Cloud account and CopilotKit API key
  • The project repository

Steps

  1. In the frontend folder, rename example.env to .env and set NEXT_PUBLIC_CPK_PUBLIC_API_KEY.

  2. From the frontend folder, install dependencies with pnpm i.

  3. Build and start the project with pnpm run build && pnpm run start.

Expected outcome

The documented frontend build and start commands have been run.

Guide limitations

  • The README states Copilot Cloud is required to run the project.
  • This guide covers frontend setup, not configuration or execution of the optional MCP agent backend.
Documentation 1 ↗
Source-based practical guide

Configure and start the optional MCP agent backend

Prepare the included MCP agent backend and start its local LangGraph development server.

Before you start

  • The project repository
  • OpenAI API key
  • LangSmith API key
  • Poetry

Steps

  1. In the agent folder, rename example.env to .env and set OPENAI_API_KEY and LANGSMITH_API_KEY.

  2. From the agent folder, run poetry install.

  3. Start the development server with poetry run langgraph dev --host localhost --port 8123 --no-browser.

Expected outcome

The README's command starts the LangGraph development server locally on port 8123.

Guide limitations

  • This is the optional backend setup; the README does not describe it as a replacement for the Copilot Cloud requirement.
  • Connecting the local backend to the interface requires the separate tunnel instructions.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
CopilotKit/open-multi-agent-canvas · Official homepage title · retained in its source language
How we review sourcesSuggest a correction