{"data":{"slug":"open-multi-agent-open-multi-agent","name":"open-multi-agent","tagline":"Orchestrates AI agents with dynamic workflows via runtime task planning.","github_url":"https://github.com/open-multi-agent/open-multi-agent","owner":"open-multi-agent","repo":"open-multi-agent","owner_avatar_url":"https://avatars.githubusercontent.com/u/279300633?v=4","primary_language":"TypeScript","stars":6943,"forks":2433,"topics":["agent-framework","agent-orchestration","agentic-ai","ai-agents","ai-governance","anthropic","claude","claude-code","deepseek","gemini","llm","local-llm","mcp","multi-agent","observability","ollama","openai","self-hosted","typescript"],"archived":false,"github_pushed_at":"2026-09-18T19:14:04+00:00","maintenance_label":"Very active","stars_delta_30d":175,"url":"https://www.graphcanon.com/tools/open-multi-agent-open-multi-agent","markdown_url":"https://www.graphcanon.com/tools/open-multi-agent-open-multi-agent.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/open-multi-agent-open-multi-agent","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=open-multi-agent-open-multi-agent","description":"Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.","homepage_url":"https://open-multi-agent.com/go/repo","license":"MIT","open_issues":4,"watchers":58,"ai_summary":"A TypeScript-based framework for coordinating AI agents across various language models, including open ones like Claude and ChatGPT.","readme_excerpt":"## License\n\nMIT\n\nMaintained by [YuanASI (Shenzhen YuanASI Technology Co., Ltd.)](https://yuanasi.com/en?utm_source=github&utm_medium=readme_footer&utm_campaign=open_multi_agent).","github_created_at":"2026-03-31T19:07:34+00:00","created_at":"2026-07-15T10:58:01.82153+00:00","updated_at":"2026-09-20T04:58:50.637301+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"agent-framework","name":"agent-framework"},{"slug":"agent-orchestration","name":"agent-orchestration"},{"slug":"agentic-ai","name":"agentic-ai"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"anthropic","name":"anthropic"},{"slug":"claude","name":"claude"},{"slug":"local-llm","name":"local-llm"},{"slug":"multi-agent","name":"multi-agent"}],"trust":{"provenance":{"is_fork":false,"github_id":1197656406,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T04:58:48.228Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":14,"days_since_push":1,"last_release_at":"2026-09-18T19:14:05Z","stars_delta_30d":175,"open_issues_delta_30d":-7},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:58:03.100Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-20T04:58:49.252Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-20T04:58:49.252Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-20T04:58:49.252Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T04:58:49.252Z"}},"decision_facts":{"hosting":{"model":"self_hosted"},"pricing":null,"requirements":null,"constraints":{"hosting_model":"self_hosted"},"when_to_use":["- When you need to dynamically plan task DAGs (Directed Acyclic Graphs) at runtime and execute them across different LLMs, such as Claude or ChatGPT.","- If your project requires a crewAI alternative that can operate with an extensive range of language models, including newer ones like Gemini."],"when_not_to_use":["- Avoid using open-multi-agent if you are looking for a ready-to-use solution for simple scripts or single-model tasks where runtime planning is not required.","- Do not use this framework if your application strictly requires support for proprietary or custom language models not listed as supported options."],"source":"enrich:decision_facts","observed_at":"2026-07-17T10:09:04.783Z"},"constraint_facets":{"hosting_model":"self_hosted"},"decision_summary":[{"label":"Hosting","value":"self hosted"},{"label":"Adopt for","value":"Provides TypeScript-based orchestration for dynamic AI workflows with support for multiple language models including open platforms."},{"label":"License detail","value":"MIT License"}]}}