# SciPhi-AI/R2R

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

Repository: https://github.com/SciPhi-AI/R2R
Canonical: https://ross.abutalabs.com/products/r2r
Language: Python
License: MIT
License Family: permissive
Topics: artificial-intelligence, large-language-models, retrieval-augmented-generation, search, question-answering, retrieval-systems, python, rag
Last push: 2025-11-07T01:02:44+00:00

## Health v2 (maintenance only)
Score: 50/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 50, release rhythm 40, longevity 66
- inputs: {"age_days": 933, "days_push": 300, "days_rel": 453, "gap_med": 4.0, "n_releases_24m": 37}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7978, forks 645 (observed 2026-08-28T04:10:10.450923+00:00)

## What it is
R2R is a production-ready AI retrieval system implementing agentic Retrieval-Augmented Generation (RAG) with a RESTful API. It provides state-of-the-art document ingestion, retrieval, and question-answering capabilities for building LLM-powered applications.

## Use cases
- build a production RAG pipeline over my documents
- serve a question-answering API backed by LLMs
- deploy an agentic retrieval system with REST endpoints
- ingest and search documents with vector retrieval
- add retrieval-augmented generation to my application

## When to choose
- you need a deployable, API-first RAG system rather than a bare library
- you want agentic RAG with document ingestion out of the box
- you prefer Python and self-hosting with an MIT license

## When to avoid
- you only need a simple vector database client
- you want a fully managed hosted RAG service
- you need a non-Python stack

## Facets
- artifact type: framework
- maturity: active
- function: rag, search-engine, api-framework, llm-inference, agent-framework
- domain: large-language-models, artificial-intelligence
- platform: python, self-hosted
- tags: retrieval-systems, question-answering, vector-search, restful-api, production-rag, retrieval-augmented-generation, search, docker, web-server

## Member repositories
- SciPhi-AI/R2R (main) score 50

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:10.450923+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:32:35.490046+00:00, confidence not recorded.
  - readme: https://github.com/SciPhi-AI/R2R (fetched 2026-08-28T04:10:10.450923+00:00, sha 8ec1078c345e)
- Data as of 2026-08-30T08:39:29.467469+00:00.