#5151st of 70 in Agent frameworks and SDKs
open-multi-agent
TypeScript runtime for multi-agent teams with approval gates and offline run review
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 7k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
Missed the latest GitHub check; these facts may be older.
Overview
OMA is a TypeScript library that coordinates teams of agents. In runTeam(), one model call plans a task graph, a deterministic scheduler executes it, and a second call writes the final answer. It adds durable human approvals, a run journal checked offline with verifyRun(), and an offline Run Viewer. It has no telemetry or hosted backend.
Who it is for: TypeScript teams building auditable multi-agent workflows with human approval
Strengths
- Three modes: runAgent, runTasks for explicit pipelines, runTeam for goal-planned task graphs
- Approval gates before plans, tasks or tool calls; persistent storage lets restarts resume
- Offline Run Viewer and run journal; no telemetry or hosted control plane
- Egress policy (offline or allowlist) checked before built-in adapters connect
Weaknesses
- TypeScript and Node.js only; Node 20 is upstream-EOL and slated for removal
- Approval UI and notifications must be built by the application
- verifyRun() checks consistency only; it does not prove the journal was never edited
- Process and ACP external-agent backends sit outside the egress policy
What it needs
- no GPU
- Needs Node.js 20+
- Models: Anthropic, OpenAI, Azure OpenAI, Bedrock, Gemini
Also in Agent frameworks and SDKs
See all 70| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 94 out of 100 |
| 2 | langchainPython framework for building LLM agents and apps from interoperable components | 89 out of 100 |
| 3 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| #4 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 89 out of 100 |
| #5 | mastraTypeScript framework for building AI agents and workflows | 89 out of 100 |