What it does
Open Multi-Agent is a code library for running AI agents, alone or in teams, on your own systems. Actions that matter, like changing files or running commands, can pause until a person approves them.
Every run leaves a record that its makers say can be checked later to prove exactly what happened. It works with cloud AI providers or local models such as Ollama, and the README says it has no tracking and no hosted control service.
Who it's for
Developers and organisations that want AI agents with human sign-off and a clear audit trail.
Can I use it without coding?
Developers only. It is a TypeScript library that needs Node.js and programming. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Server
- Computer
- An ordinary computer is fine
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe