Open source retrieval-augmented-generation projects
Every project in the registry tagged retrieval-augmented-generation, ranked by real GitHub adoption.
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
Get instant answers from your company knowledge
Distributed vector search for AI-native applications
Manifold is an experimental platform for enabling long horizon workflow automation using teams of AI assistants.
Related tags
Frequently asked questions
How many open source retrieval-augmented-generation projects are there?
This registry tracks 8 projects tagged retrieval-augmented-generation, with 111,669 GitHub stars between them. The most-adopted is LightRAG at 40,487 stars.
Are these retrieval-augmented-generation projects free to use?
Yes — 8 of the 8 carry an explicit open-source licence across 2 distinct licences, so there is no licence fee. Where a project also sells a hosted or enterprise version, the self-hosted path remains free.
Which retrieval-augmented-generation project should I choose?
The list above is ranked by GitHub stars, but stars measure attention rather than fit. Check three things on each card: the licence (permissive versus copyleft), the language it is written in, and the last-push date — a high-star project that has not been pushed in a year is a liability.
Are these retrieval-augmented-generation projects still maintained?
6 of the 8 were pushed in the last 90 days, and every card shows its exact last-push date so you can see the rest. Sort your shortlist by that date before committing to a migration.