← back to the directory
Application Retrieval & MemoryApps & UIs

R2R

1Production-ready 2RAG 3engine 4with 5retrieval 6API

the six Ws · specification

W1 Who

Maintained by SciPhi AI.

W2 What

A production RAG engine with ingestion and a retrieval API.

W3 Where

Self-hosted via Docker, with a REST API.

W4 When

When you need RAG over documents behind an API.

W5 Why

Bundles ingestion, retrieval, and orchestration for RAG at scale.

W6 With

Docker, a vector store, and an LLM provider.

W7 Watch

Company-maintained; open-source (MIT), self-hostable. Runs on your infrastructure; calls the LLM and embedding providers you configure.

RAGRetrievalSelf-hosted

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.