{"data":{"slug":"langchain-ai-open-swe","name":"open-swe","tagline":"An Open-Source Asynchronous Coding Agent","github_url":"https://github.com/langchain-ai/open-swe","owner":"langchain-ai","repo":"open-swe","owner_avatar_url":"https://avatars.githubusercontent.com/u/126733545?v=4","primary_language":"Python","stars":10576,"forks":1228,"topics":["agent","agents","ai","anthropic","claudecode","llm","llms","openai"],"archived":false,"github_pushed_at":"2026-08-19T11:57:07+00:00","maintenance_label":"Very active","stars_delta_30d":221,"url":"https://www.graphcanon.com/tools/langchain-ai-open-swe","markdown_url":"https://www.graphcanon.com/tools/langchain-ai-open-swe.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/langchain-ai-open-swe","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=langchain-ai-open-swe","description":"An Open-Source Asynchronous Coding Agent","homepage_url":"https://www.langchain.com/blog/open-swe-an-open-source-framework-for-internal-coding-agents","license":"MIT","open_issues":28,"watchers":49,"ai_summary":"Open-source project focused on developing an asynchronous coding agent capable of interacting with user organizations via customizable components like models, sandboxes, tools, triggers, prompts, and middleware.","readme_excerpt":"## Getting Started\n\n- **[Installation Guide](docs/INSTALLATION.md)** — local dev (backend + dashboard), GitHub App creation, LangSmith, Linear/Slack/GitHub triggers, and production deployment\n- **macOS Desktop beta** — clone this repository and run `make install-desktop` from the root to install or update the app\n- **[Customization Guide](docs/CUSTOMIZATION.md)** — swap the sandbox, model, tools, triggers, system prompt, and middleware for your org","github_created_at":"2025-05-21T21:44:24+00:00","created_at":"2026-07-07T17:39:26.46033+00:00","updated_at":"2026-08-19T12:01:09.433438+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":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"ai","name":"ai"},{"slug":"anthropic","name":"anthropic"},{"slug":"claudecode","name":"claudecode"},{"slug":"llm","name":"llm"},{"slug":"openai","name":"openai"}],"trust":{"provenance":{"is_fork":false,"github_id":987975584,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-19T12:01:08.521Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":0,"days_since_push":0,"last_release_at":null,"stars_delta_30d":221,"open_issues_delta_30d":4},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:14:35.278Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-08-19T12:01:09.054Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-08-19T12:01:09.054Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-19T12:01:09.054Z","managed_saas":false},"languages":{"value":["python","javascript"],"source":"github.language+package.json+pyproject.toml","observed_at":"2026-08-19T12:01:09.054Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-19T12:01:09.054Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-19T12:01:09.054Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["If you are integrating with Linear/Slack/GitHub workflows specifically as it seems to support these platforms natively.","Suitable for teams who want extensive control over different aspects such as the model used, sandbox environment, system prompts, etc."],"when_not_to_use":["Not recommended if you require real-time interaction with coding agents instead of asynchronous communication.","Avoid choosing this tool if your project does not align well with customization options provided or if integration complexity outweighs benefits."],"source":"enrich:decision_facts","observed_at":"2026-07-11T15:53:32.985Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"open-swe is an open-source asynchronous coding agent that allows customization of components like models, sandboxes, tools, triggers, prompts, and middleware."}]}}