{"data":{"slug":"sciphi-ai-r2r","name":"R2R","tagline":"SoTA production-ready AI retrieval system with RESTful API","github_url":"https://github.com/SciPhi-AI/R2R","owner":"SciPhi-AI","repo":"R2R","owner_avatar_url":"https://avatars.githubusercontent.com/u/148402514?v=4","primary_language":"Python","stars":7999,"forks":647,"topics":["artificial-intelligence","large-language-models","python","question-answering","rag","retrieval-augmented-generation","retrieval-systems","search"],"archived":false,"github_pushed_at":"2025-11-07T01:02:44+00:00","maintenance_label":"Slowing","stars_delta_30d":32,"url":"https://www.graphcanon.com/tools/sciphi-ai-r2r","markdown_url":"https://www.graphcanon.com/tools/sciphi-ai-r2r.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sciphi-ai-r2r","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sciphi-ai-r2r","description":"SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.","homepage_url":null,"license":"MIT","open_issues":126,"watchers":45,"ai_summary":"SciPhi-AI/R2R is a state-of-the-art retrieval system that supports retrieval-augmented generation (RAG) and offers a RESTful API for integration. It is built in Python and can be deployed via Docker.","readme_excerpt":"# Quick install and run in light mode\npip install r2r\nexport OPENAI_API_KEY=sk-...\npython -m r2r.serve\n\n---\n\n# docker compose -f compose.full.yaml --profile postgres up -d\n```\n\nFor detailed self-hosting instructions, see the [self-hosting docs](https://r2r-docs.sciphi.ai/self-hosting/installation/overview).","github_created_at":"2024-02-12T03:24:27+00:00","created_at":"2026-07-07T17:34:24.433436+00:00","updated_at":"2026-09-20T04:33:53.585379+00:00","categories":[{"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"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"artificial-intelligence","name":"artificial-intelligence"},{"slug":"large-language-models","name":"large-language-models"},{"slug":"python","name":"python"},{"slug":"question-answering","name":"question-answering"},{"slug":"rag","name":"rag"},{"slug":"retrieval-augmented-generation","name":"retrieval-augmented generation"},{"slug":"retrieval-systems","name":"retrieval-systems"},{"slug":"search","name":"search"}],"trust":{"provenance":{"is_fork":false,"github_id":756142546,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:51:14.746Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":315,"last_release_at":"2025-06-06T22:42:56Z","stars_delta_30d":32,"open_issues_delta_30d":4},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:51:16.908Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:51:13.662Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:51:13.662Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:51:13.662Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The core R2R system is free to use under the MIT License, but additional services or integrations may incur costs."},"requirements":{"notes":["Requires Docker for deployment.","Python environment is necessary for installation and operation."],"min_ram_gb":4,"requires_docker":true},"constraints":{"min_ram_gb":4,"pricing_model":"freemium","requires_docker":true},"when_to_use":["When you need a production-ready AI retrieval system that supports retrieval-augmented generation (RAG) and can be integrated via RESTful API.","If your project requires Python-based development and you prefer deployment through Docker for consistency and ease of setup."],"when_not_to_use":["If your project does not require retrieval-augmented generation (RAG) capabilities, as R2R is specifically designed with this feature.","If you are looking for a tool that does not require Docker for deployment, as R2R is optimized for Docker-based setups."],"source":"enrich:decision_facts","observed_at":"2026-09-18T10:53:32.855Z"},"constraint_facets":{"min_ram_gb":4,"pricing_model":"freemium","requires_docker":true},"decision_summary":[{"label":"Pricing","value":"freemium - The core R2R system is free to use under the MIT License, but additional services or integrations may incur costs."},{"label":"Requirements","value":"Min 4 GB RAM; Requires Docker; Requires Docker for deployment.; Python environment is necessary for installation and operation."},{"label":"Adopt for","value":"R2R is a state-of-the-art retrieval system that supports retrieval-augmented generation (RAG) and offers a RESTful API for integration, built in Python and deployable via Docker."},{"label":"License detail","value":"MIT License"}]}}