API or serverResearch and knowledge
R2R
Build multimodal search, RAG, and deep research over your own knowledge base.
- Stars
- 7,926
- Forks
- 644
- Updated
- Updated Jul 10, 2026
MIT
Build multimodal search, RAG, and deep research over your own knowledge base.
R2R ingests documents, images, audio, and other content into a self-hosted knowledge base, then exposes hybrid search, cited RAG, knowledge graphs, and a multi-step research agent through a REST API. Python and JavaScript clients handle document management and retrieval. It can run in a lightweight mode or a fuller Docker deployment, and normally requires an API key for the selected language model.
Resource types
Use cases
Runtime
Search and score websites by how usable they are for AI agents
Build configurable RAG search and chat inside your own infrastructure.
Protocols & integrations
Public GitHub facts last synced Jul 10, 2026.
Research the past month across social platforms, developer communities, and the web.
Self-host team AI chat, knowledge retrieval, research, and custom agents across LLMs.