{"data":{"slug":"marker-inc-korea-autorag","name":"AutoRAG","tagline":"Open-source framework for RAG evaluation and optimization via AutoML","github_url":"https://github.com/Marker-Inc-Korea/AutoRAG","owner":"Marker-Inc-Korea","repo":"AutoRAG","owner_avatar_url":"https://avatars.githubusercontent.com/u/74290595?v=4","primary_language":"TypeScript","stars":4968,"forks":419,"topics":["analysis","automl","benchmarking","document-parser","embeddings","evaluation","llm","llm-evaluation","llm-ops","open-source","ops","optimization","pipeline","python","qa","rag","rag-evaluation","retrieval-augmented-generation"],"archived":false,"github_pushed_at":"2026-08-05T14:46:13+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/marker-inc-korea-autorag","markdown_url":"https://www.graphcanon.com/tools/marker-inc-korea-autorag.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/marker-inc-korea-autorag","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=marker-inc-korea-autorag","description":"AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.","homepage_url":"https://marker-inc-korea.github.io/AutoRAG/","license":"Apache-2.0","open_issues":123,"watchers":34,"ai_summary":"AutoRAG provides tools for automating retrieval-augmented generation tasks, focusing on evaluation and optimization with support for Python.","readme_excerpt":"## Installation\n\nPublished as `@autorag/librarian` (dist bundled with Bun, runtime Node ≥ 24 or Bun):\n\n```bash\nbun add @autorag/librarian          # library\nbun install -g @autorag/librarian   # autorag CLI\n\n---\n\n## Quick Start\n\n```typescript\nimport { AutoRAGAgent } from \"@autorag/librarian\";\n\nconst agent = new AutoRAGAgent({\n  searchPaths: [\"/path/to/documents\"],\n});\n\nconst response = await agent.searchDocuments(\"summarize the compliance requirements\");\nconsole.log(response.answer);\nfor (const result of response.results) {\n  console.log(`[${result.number}] ${result.title} — ${result.summary}`);\n}\n\n// Mark which results were useful — AutoRAG remembers for next time\nagent.recordFeedbackByNumbers(response.sessionId, [1, 3], [2]);\n```\n\n`searchDocuments()` runs the Pi agent loop — it searches, reads, consults memory, curates, and finalizes through the `emit_autorag_results` structured tool — then returns a typed `SearchDocumentsResponse`. The caller consumes the structured payload directly; no assistant text parsing.","github_created_at":"2024-01-10T12:25:00+00:00","created_at":"2026-07-11T10:41:38.414194+00:00","updated_at":"2026-08-08T00:00:56.484238+00:00","categories":[{"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"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"analysis","name":"analysis"},{"slug":"automl","name":"automl"},{"slug":"benchmarking","name":"benchmarking"},{"slug":"document-parser","name":"document-parser"},{"slug":"embeddings","name":"embeddings"},{"slug":"evaluation","name":"evaluation"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"optimization","name":"optimization"}],"trust":{"provenance":{"is_fork":false,"github_id":741450201,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-08T00:00:47.434Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":4,"days_since_push":2,"last_release_at":"2026-07-24T01:52:23Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:41:42.765Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-08-08T00:00:48.052Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-08-08T00:00:48.052Z"},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-08-08T00:00:48.052Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-08-08T00:00:48.052Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-08T00:00:48.052Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Automated benchmarking is needed for retrieval-augmented generation tasks","Desire to optimize Python pipeline with machine learning-driven automation"],"when_not_to_use":["Requirements exceed capabilities of open-source tools","No need for RAG-specific optimization and evaluation features"],"source":"enrich:decision_facts","observed_at":"2026-07-15T08:37:17.236Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"AutoRAG: Automate RAG task evaluation and optimization using AutoML techniques."},{"label":"License detail","value":"Apache-2.0 licensed, allowing free use in commercial projects while retaining copyright notices."}]}}