{"data":{"slug":"rath-team-openrath","name":"OpenRath","tagline":"An open-source runtime for dynamic multi-agent workflows","github_url":"https://github.com/Rath-Team/OpenRath","owner":"Rath-Team","repo":"OpenRath","owner_avatar_url":"https://avatars.githubusercontent.com/u/279513473?v=4","primary_language":"Python","stars":1100,"forks":52,"topics":["agent-framework","agentic-ai","ai-agents","anthropic","lllm-agent","llm","memory","model-context-protocol","multi-agent","multi-agent-systems","open-source","openai","provenance","python","runtime-state","sandbox","session-graph","session-state","workflow-orchestration"],"archived":false,"github_pushed_at":"2026-07-22T18:29:53+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/rath-team-openrath","markdown_url":"https://www.graphcanon.com/tools/rath-team-openrath.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rath-team-openrath","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rath-team-openrath","description":"An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.","homepage_url":"https://www.openrath.com/","license":"BSD-3-Clause","open_issues":4,"watchers":21,"ai_summary":"OpenRath is an open-source runtime developed in Python that supports dynamic multi-agent and multi-session workflows similar to PyTorch's capabilities but tailored for AI agents.","readme_excerpt":"## Quick Install\n\n```bash\npip install openrath\n```\n\nOptional sandbox and memory integrations:\n\n```bash\npip install \"openrath[opensandbox]\"\npip install \"openrath[openviking]\"\n```\n\nFor source development:\n\n```bash\ngit clone https://github.com/Rath-Team/OpenRath.git\ncd OpenRath\nuv sync --group dev --group docs\n```\n\nMost LLM examples use OpenAI-compatible environment variables:\n\n```bash\nexport OPENAI_API_KEY=sk-...\nexport OPENAI_BASE_URL=https://your-gateway/v1\nexport OPENAI_DEFAULT_MODEL=your-model-name\n```\n\nYou can also configure providers in `~/.openrath/config.json`. Environment variables take precedence.\n\n---\n\n---\n\n## License\n\nOpenRath uses a BSD-style license. See [LICENSE](LICENSE).","github_created_at":"2026-05-04T13:27:24+00:00","created_at":"2026-07-11T11:52:45.801019+00:00","updated_at":"2026-07-27T06:00:24.22923+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":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"}],"tags":[{"slug":"agent-framework","name":"agent-framework"},{"slug":"agentic-ai","name":"agentic-ai"},{"slug":"memory","name":"memory"},{"slug":"multi-agent-systems","name":"multi-agent-systems"},{"slug":"open-source","name":"open-source"},{"slug":"runtime-state","name":"runtime-state"},{"slug":"session-graph","name":"session-graph"},{"slug":"workflow-orchestration","name":"workflow-orchestration"}],"trust":{"provenance":{"is_fork":false,"github_id":1228880861,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-27T06:00:23.211Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":6,"days_since_push":4,"last_release_at":"2026-07-08T01:25:57Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:52:47.047Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-27T06:00:23.723Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-27T06:00:23.723Z"},"license_spdx":{"value":"BSD-3-Clause","source":"github.license","observed_at":"2026-07-27T06:00:23.723Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You need to simulate complex interactions between multiple AI agents in real-time scenarios where dynamic changes are frequent.","Your project requires a provenance tracking system for multi-agent systems to audit actions and decisions made by the agents."],"when_not_to_use":["If you are working on single-agent tasks with limited or no need for interaction between agents, OpenRath's capabilities may be overkill.","When your focus is exclusively on model training rather than runtime workflows and interactions, other libraries or frameworks might offer more direct support."],"source":"enrich:decision_facts","observed_at":"2026-07-16T22:16:53.421Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"OpenRath highlights its unique capabilities in managing multi-agent workflows dynamically, offering an open-source runtime with Python integration that rivals PyTorch but focuses on AI agents and their sessions."}]}}