Open-source project

Open Multi-Agent

open-multi-agent/open-multi-agent

Self-hosted agent runtime with durable approvals.

Runtimes & Sandboxes Safety & Red-teaming

Open Multi-Agent is the open-source runtime behind QM: a self-hosted TypeScript agent runtime with durable approvals and verifiable run records — 'own it, approve it, audit it' — built for multiplayer agent work.

View on GitHub Homepage

Behind the project

QM

A multiplayer agent harness for work.

QM gives every person and shared room a durable, isolated agent workspace while keeping administration, permissions and background work centralized — docs cover models and harnesses, sandboxes, apps and skills, and Slack/web surfaces. Its open-source runtime (open-multi-agent) ships durable approvals and verifiable run records.

2026

Related projects

Hermes Agent

NousResearch/hermes-agent

Featured

The agent that grows with you.

Nous Research's self-improving personal agent: a learning loop turns experience into reusable skills, builds a persistent user model across sessions, and checkpoints state to disk with rollback — lean enough for a $5 VPS and driven from the chat apps you already use.

≈250kTypeScriptMIT

Browser Use

browser-use/browser-use

Featured

Make websites accessible for AI agents.

Browser Use gives agents a fast, vision-capable browser: DOM extraction, multi-tab workflows, element tracking and self-correction. The default open-source library for web-operating agents.

≈117kPythonMIT

OpenHands

OpenHands/OpenHands

Featured

The open platform for cloud coding agents.

OpenHands (formerly All Hands AI) is an open-source coding agent platform — agent canvas, sandboxed execution, SDK and an enterprise control plane — with 500+ contributors and millions of downloads.

≈90kTypeScriptMIT