Self-host R2R
v3.6.5Agentic RAG retrieval engine with a REST API
- Stars
- 8 045
- Ports
- 8000 (API server port inside the provided Docker image (R2R_PORT).), 7272 (Port the RESTful API is accessed on locally (base_url in SDK examples).)
What is R2R?
R2R is an open-source AI retrieval system built around a RESTful API, aimed at developers adding retrieval-augmented generation to their own applications. It ingests multimodal content (text, PDF, JSON, images, audio), searches with hybrid semantic + keyword retrieval using reciprocal rank fusion, extracts entities and relationships into knowledge graphs, and offers a Deep Research API that performs multi-step reasoning over your knowledge base and/or the internet. Document management and a complete user authentication and access-management system are included. You can run it quickly in light mode with pip install r2r and python -m r2r.serve, or in full mode via Docker Compose with Postgres, configuring LLM provider keys such as OpenAI and Anthropic through environment variables. Python and JavaScript SDKs talk to the API. Official documentation lives at r2r-docs.sciphi.ai, which returned 404 when checked, and the repository was last pushed in November 2025.
Should you self-host R2R?
R2R scores 59/100 on selfhost.directory (how scoring works) and ranks #6 of 7 in RAG. It has 8 045 GitHub stars.
There was no stable release in the past 12 months, so check the repository's recent activity before you rely on it.
Setup is moderate: expect some configuration beyond a single command. It is MIT-licensed and written mostly in Python.
Its closest alternative on selfhost.directory is WeKnora (83/100, 35 728 stars). It scores higher overall, so compare the two before you pick. See R2R vs WeKnora side by side.
Features
- Agentic RAG / deep research
- Document Management
- Hybrid Search
- Knowledge Graph Extraction
- Multimodal ingestion
- REST API
- Retrieval-augmented generation (RAG)
- User & access management
R2R README
More in RAG
ragSelf-hosted, open-source retrieval-augmented generation chat app on txtai and Streamlit: vector RAG plus graph path queries, with your own LLM.
SeekStormOpen-source Rust search engine with BM25 lexical and vector search fused in one hybrid query, multi-tenant REST server, web UI and MCP support. Self-hosted, free forever.
supermemorySelf-hosted AI memory and context server: Supermemory Local extracts facts, builds user profiles, and blends RAG with memory search through one API on port 6767.
surfsenseSelf-hosted, open-source NotebookLM alternative: an air-gapped desktop AI agent that researches, edits and transforms your documents with any local or hosted model.
TaskingAIAn open-source, self-hosted BaaS stack for building LLM agents: unified model APIs, RAG, built-in tools and an admin console, deployed with Docker Compose.
UtopiaSelf-hosted, open-source enterprise world model: a Rust binary plus Postgres/pgvector holding a bitemporal knowledge graph, with agentic RAG chat and an MCP server.
VaneSelf-hosted, open-source AI answering engine: searches via bundled SearxNG and answers with cited sources, using local Ollama models or OpenAI, Claude and Gemini.
vortexSelf-hosted RAG application for document chat with multiple LLM providers. Combines vector and keyword search, re-ranks results, and shows source citations.
WeKnoraTencent's open-source knowledge framework for teams: self-hosted RAG Q&A with citations, agents with sandboxed skills, and auto-generated wikis on swappable LLMs.
YuxiYuxi is an open-source, self-hosted knowledge agent platform combining Agentic RAG, Neo4j knowledge graphs, LangGraph multi-agent runs, MCP/Skills and sandboxes.
AGmindAGMind is a self-hosted, open-source installer deploying a private RAG stack on NVIDIA DGX Spark in ~30 minutes via an interactive wizard.
bishengAn Apache-2.0, self-hosted LLM devops platform for enterprise AI: GenAI workflows, RAG knowledge bases, agents, model management, evaluation, SFT and OCR.
0 comments