ragi-toolkit is a Python library and MCP server that provides an eval-first, agent-agnostic approach to Retrieval-Augmented Generation. It allows developers to define retrieval contracts, measure performance, iterate on results, and ship portable components that any agent can consume. Features support for embeddings, BM25, and comprehensive evaluation tools.
ragi-toolkit is an AI & ML project. It focuses on building measurable, portable, and evolvable retrieval systems for RAG applications without being tied to specific agents. ragi-toolkit is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the command line and API, and it can be self-hosted.
Behind ragi-toolkit is Hedy Pamungkas, and it first shipped in 2026. Development happens publicly on GitHub with 11 commits in the last 90 days. Among its 5 catalogued features are RAG Evaluation, Retrieval Contract, and Embeddings Support. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do