Open-source agentic Retrieval-Augmented Generation (RAG) system with a RESTful API.
At a Glance
Self-hosted R2R core released under the MIT License.
Engagement
Available On
Alternatives
Listed Oct 2026
About R2R
R2R is an open-source retrieval system from SciPhi-AI that combines agentic Retrieval-Augmented Generation (RAG) with a RESTful API. The repository describes it as a production-ready AI retrieval system, written in Python and released under the MIT License. The latest release listed is v3.6.5, published on 2025-06-06.
What It Is
R2R is a retrieval-augmented generation system for building question-answering and search applications on top of large language models. It exposes its functionality through a RESTful API, so applications can call retrieval and generation features over HTTP. The project's GitHub topics reference question answering, retrieval systems, and search.
Open-Source Availability
The source code is public on GitHub under the MIT License. The repository README points to a Python package readme, so detailed setup and usage steps are not included in the supplied material.
Community Discussions
Be the first to start a conversation about R2R
Share your experience with R2R, ask questions, or help others learn from your insights.
Pricing
Open Source (MIT)
Self-hosted R2R core released under the MIT License.
- MIT License
- Agentic Retrieval-Augmented Generation (RAG) with a RESTful API
- Source code publicly available on GitHub
Capabilities
Key Features
- Agentic Retrieval-Augmented Generation (RAG)
- RESTful API
- Question answering
- Retrieval and search system
- MIT-licensed open source