# open-multi-agent/open-multi-agent

TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it on any LLM (Claude, ChatGPT, Gemini, DeepSeek, or local models).

Repository: https://github.com/open-multi-agent/open-multi-agent
Canonical: https://ross.abutalabs.com/products/open-multi-agent
Homepage: https://open-multi-agent.com
Language: TypeScript
License: MIT
License Family: permissive
Topics: agent-framework, ai-agents, claude, llm, multi-agent, openai, typescript, anthropic, nodejs, ollama, deepseek, gemini, local-llm, mcp, crewai-alternative, langgraph-alternative, agent-orchestration, agentic-ai, claude-code, dynamic-workflows
Last push: 2026-08-25T16:11:53+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 11
- inputs: {"age_days": 155, "days_push": 8, "days_rel": 12, "gap_med": 6, "n_releases_24m": 22}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6831, forks 2427 (observed 2026-08-28T04:09:48.890883+00:00)

## What it is
Open Multi-Agent (OMA) is an MIT-licensed TypeScript framework for multi-agent AI orchestration that runs inside Node.js backends. A coordinator decomposes a goal into a task DAG at runtime, a deterministic scheduler executes tasks in parallel across a team of agents on any LLM provider (Claude, GPT, Gemini, DeepSeek, Ollama, or OpenAI-compatible endpoints), and every run is traceable, resumable, and replayable via an offline Run Viewer.

## Use cases
- orchestrate multiple AI agents on a single goal in a Node.js backend
- decompose a goal into a parallel task DAG without hand-building the workflow graph
- run a security review or PR review as a coordinated multi-agent team
- mix models per agent, including local models via Ollama
- include external coding agents (via ACP) as team members in one task DAG
- trace, approve, budget, and replay multi-agent runs
- get schema-validated structured output from agent tasks

## When to choose
- a goal benefits from multiple specialist roles and parallelizable work
- you want runtime planning instead of maintaining a fixed workflow graph
- you need orchestration embedded in an existing Node.js/TypeScript backend
- you want provider-agnostic model access with tracing and resumability

## When to avoid
- one model call already solves the task
- every step and transition must be fixed and deterministic
- you only need a provider SDK or a chat UI
- you want to avoid the extra cost of a planning model call

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, mcp, workflow-automation, sdk
- domain: large-language-models, developer-tools, backend
- platform: cross-platform, self-hosted
- tags: multi-agent, agent-orchestration, task-dag, dynamic-workflows, crewai-alternative, langgraph-alternative, openai, anthropic, claude, gemini, deepseek, ollama, local-llm, opentelemetry, acp, run-viewer, structured-output, ai-agents, automation, nodejs, typescript

## Member repositories
- open-multi-agent/open-multi-agent (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:48.890883+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:41:53.178857+00:00, confidence not recorded.
  - readme: https://github.com/open-multi-agent/open-multi-agent (fetched 2026-08-28T04:09:48.890883+00:00, sha 9780bbd0ae1e)
  - homepage: https://open-multi-agent.com (fetched 2026-08-29T08:38:21.454688+00:00, sha f90d8c834281)
  - site_page: https://open-multi-agent.com/getting-started/three-ways-to-run (fetched 2026-08-29T08:38:21.464084+00:00, sha 2793fe2b274b)
  - site_page: https://open-multi-agent.com/getting-started/introduction (fetched 2026-08-29T08:38:21.469838+00:00, sha aecb2e9d9eb0)
  - site_page: https://open-multi-agent.com/getting-started/quick-start (fetched 2026-08-29T08:38:21.474949+00:00, sha ff50742644e4)
  - site_page: https://open-multi-agent.com/about (fetched 2026-08-29T08:38:21.476641+00:00, sha fcd4bf4befc9)
  - site_page: https://open-multi-agent.com/integrations/external-agents (fetched 2026-08-29T08:38:21.466122+00:00, sha bc0139395cd5)
  - site_page: https://open-multi-agent.com/integrations (fetched 2026-08-29T08:38:21.467985+00:00, sha d11aaff5964b)
  - site_page: https://open-multi-agent.com/changelog (fetched 2026-08-29T08:38:21.471708+00:00, sha b80d25a21d29)
- Data as of 2026-08-30T08:39:29.467469+00:00.