← back to the directory
Library / SDK Observability & EvaluationRetrieval & Memory

AutoRAG

1Automatically 2find 3your 4best 5RAG 6pipeline

the six Ws · specification

W1 Who

Maintained by Marker Inc.

W2 What

Automatically finds the best RAG pipeline for data.

W3 Where

A Python library run locally or in CI.

W4 When

When optimizing a RAG stack against your data.

W5 Why

Benchmarks RAG modules to pick the best combination.

W6 With

Python, your data, and an LLM provider.

W7 Watch

Company-maintained; open-source (Apache-2.0), self-runnable. Evaluation runs locally; LLM-based metrics call the provider you configure.

RAGOptimizationEvaluation

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.