# R2R

> Self-hosted agentic RAG system with a RESTful API: multimodal ingestion, hybrid search, knowledge graphs, a Deep Research agent, and user & access management.

- **Category:** RAG
- **Licence:** MIT
- **Latest version:** v3.6.5
- **Open source:** oss
- **Languages:** Python
- **Platforms:** Docker Compose, pip
- **Tags:** Search, REST API, Document Management, Multi modal, LLM, Rag, Retrieval Augmented Generation, Vector Search, Knowledge Graph, Hybrid Search, Python, Artificial intelligence, Deep research, Large language models, Question Answering, Retrieval Systems

## Description

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.

## Links

- [Homepage](https://github.com/sciphi-ai/r2r)
- [Discord](https://discord.gg/p6KqD2kjtB)

---
Source: https://selfhost.directory/project/r2r