open-multi-agent
OMA (Open Multi-Agent) is a self-hosted TypeScript runtime aimed at organizations that need to own, approve and audit what their agents do. It offers three modes: `runAgent()` for a single agent, `runTasks()` for an explicit pipeline and `runTeam()` to plan from a goal.
Its central feature is durable approval. A plan, task dispatch or tool call can return `suspend`; the request is stored next to the checkpoint and bound to a SHA-256 hash of exactly what the reviewer saw, so the run resumes from that content after a restart, and a tampered request fails closed. Every run leaves a record that can be verified offline, byte for byte.
It has no telemetry or hosted control plane and works with hosted providers, local servers such as Ollama, vLLM and llama-server, and Chinese providers. It needs Node.js 20 or newer (the README recommends a maintained LTS), and `npm create oma-app` scaffolds starters with a demo that runs without an API key.
Features
Why choose it
Trade-offs
Maintenance check
- Last commit
- 2026-10-18
- Commits, last 90 days
- 100+
- Releases, last 90 days
- 14
- Latest release
- v1.21.3 (2026-10-16)
- Open issues
- 5
- Recent issues with at least one comment
- 3/6
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Most discussed open issues
- #147 [Tracker] Propose a cookbook example (selective intake)32 comments · 2026-04-22
- #454 Evaluate OpenAI SDK v7 support and the Node.js 22 transition2 comments · 2026-07-29
- #628 [Bug] Demo run failed1 comments · 2026-10-16
- #612 [Feature] Tool wrapper for runImage so agents can decide when to generate0 comments · 2026-09-23
- #611 [Feature] Emit runImage attempts as trace spans0 comments · 2026-09-23
Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.
Compatibility
Quick start
Use cases
Alternatives
Comments
No comments yet. Be the first!