Open source multi-agent projects
Every project in the registry tagged multi-agent, ranked by real GitHub adoption.
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat ap
Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.
Build and run agents you can see, understand and trust.
🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
Related tags
Frequently asked questions
How many open source multi-agent projects are there?
This registry tracks 7 projects tagged multi-agent, with 172,784 GitHub stars between them. The most-adopted is nanobot at 48,274 stars.
Are these multi-agent projects free to use?
Yes — 7 of the 7 carry an explicit open-source licence across 2 distinct licences, so there is no licence fee. Where a project also sells a hosted or enterprise version, the self-hosted path remains free.
Which multi-agent project should I choose?
The list above is ranked by GitHub stars, but stars measure attention rather than fit. Check three things on each card: the licence (permissive versus copyleft), the language it is written in, and the last-push date — a high-star project that has not been pushed in a year is a liability.
Are these multi-agent projects still maintained?
7 of the 7 were pushed in the last 90 days, and every card shows its exact last-push date so you can see the rest. Sort your shortlist by that date before committing to a migration.