EN DE

R2R

Production-ready AI retrieval system with agentic RAG and RESTful API

★ 7,910 GitHub MIT ragretrievalsearchknowledge-graphapiself-hosted RAG & Knowledge

Overview

R2R is an advanced AI retrieval system supporting Retrieval-Augmented Generation (RAG) with production-ready features. Built around a RESTful API, R2R offers multimodal content ingestion, hybrid search, knowledge graphs, and comprehensive document management. It includes a Deep Research API for multi-step reasoning that fetches relevant data from your knowledge base and/or the internet to deliver richer, context-aware answers for complex queries.

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  r2r:
    image: sciphiai/r2r:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/r2r:/data

Best VPS for R2R →

Related tools

LangChain

Build context-aware reasoning applications powered by LLMs

Supabase

Open-source Postgres platform for AI apps with vector search, realtime subscriptions & built-in dashboard

RedisStack

Redis with integrated modules for vector search, JSON, and search capabilities

Meilisearch

Lightning-fast search engine with AI-powered hybrid and vector search

PrivateGPT

Chat with your documents privately using LLMs — 100% local, no data leaks

Milvus

High-performance cloud-native vector database for scalable ANN search

Guides & articles

Deploy R2R in 5 Minutes: Self-Hosted RAG with Docker

Get R2R running on your own server in minutes. Step-by-step Docker deployment guide with document ingestion, semantic search, and the Deep Research agent API.

Jun 30, 2026

R2R: The Production-Ready RAG System You Can Self-Host

R2R is a production-ready AI retrieval system with agentic RAG, hybrid search, knowledge graphs, and a RESTful API. Self-host it with Docker for complete data privacy and unlimited scaling.

Jun 30, 2026