Open source rag projects
Every project in the registry tagged rag, ranked by real GitHub adoption.
One interface for every AI model you run or connect
LLM-ready web crawler built for AI data pipelines
LlamaIndex is the document processing platform for AI
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
A modular graph-based Retrieval-Augmented Generation (RAG) system
Unified AI-powered enterprise search across company data
Python scraper based on AI
Build powerful AI knowledge bases with ease
An open-source RAG-based tool for chatting with your documents.
open-source agentic AI data assistant for the next generation of AI + Data products.
Open source agentic operating system
Privacy-first knowledge base with any AI model you choose
A lightweight, lightning-fast, in-process vector database
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
World's first open-source enterprise world model.
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Build autonomous AI agents in Python.
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
Unify vector search and graph traversals in one database
Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestr
An enterprise AI development framework for building AI agents. It provides unified management of multi-provider LLMs, secure enterprise knowledge bases with hig
Context Graph for AI Native SDLC
MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）
🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
Get instant answers from your company knowledge
Jupyter Notebooks to help you get hands-on with Pinecone vector databases
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
Distributed vector search for AI-native applications
Local-first AI job intelligence workbench for scraping roles, ranking fit, and generating tailored application materials.
AI-native workspace for local shells and remote machines.Zero Webview, zero OpenSSL, zero telemetry, and no app subscription.
Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !
OpenSource Production ready Customer service with built in Evals and monitoring
Self-hosted SERP API for Google, Bing, Yandex, and more
Prismer Cloud
An open-source, local-first writing workspace where you can write with Claude Code and Codex, drawing on your own sources and past work.
Unified research workspace for humans & agents — PDF Q&A with citations, Vault, writing. 为人与 Agent 协作的科研工作台；补齐 Zotero 时代的人机上下文断点。
Build fast and accurate GenAI apps with GraphRAG SDK at scale 🌟
ID-based RAG FastAPI: Integration with Langchain and PostgreSQL/pgvector
Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.
中文优先的企业 RAG 知识库：可控解析、治理、切块、混合检索、重排、引用、图谱、评测与 Dify 接入。
The Supabase of AI era. A modular, open-source backend for building AI-native software — designed for knowledge, not static data.
Open Souce IM with AI powered live-chat, email, ticket support, omni-channel customer service，alternative to slack + zendesk/intercom/hubspot/ada/decagon/sierra
Related tags
Frequently asked questions
How many open source rag projects are there?
This registry tracks 51 projects tagged rag, with 765,514 GitHub stars between them. The most-adopted is Open WebUI at 157,575 stars.
Are these rag projects free to use?
Yes — 48 of the 51 carry an explicit open-source licence across 5 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 rag 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 rag projects still maintained?
42 of the 51 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.