modelscope
★ 3,423evalscope
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
AI channelRAG 
Open-source RAG frameworks
Retrieval-augmented generation (RAG) makes a language model answer from your own documents. The text is split into chunks, turned into vectors and stored in an index, and the most relevant chunks are added to the prompt when a question comes in. The projects here cover the whole pipeline or one part of it: document parsing, vector search, or a complete question-answering app.
How to choose
Answer quality in RAG depends mostly on retrieval, not on the model. Compare how each project handles difficult documents such as PDFs, tables and scans, whether it supports hybrid search that combines keywords with vectors and re-ranking, and whether it shows which sources an answer came from.
Most-starred projects
169–192 of 596Sumanth077
★ 3,388ai-engineering-toolkit
A curated list of 100+ libraries and frameworks for AI engineers building with LLMs
HKUDS
★ 3,367VideoRAG
[KDD'2026] "VideoRAG: Chat with Your Videos"
ANative-Lab
★ 3,328EvoAgentX
🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
docker
★ 3,326docker-agent
AI Agent Builder and Runtime by Docker Engineering
johnbean393
★ 3,311Sidekick
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.
ombharatiya
★ 3,302ai-system-design-guide
AI system design guide for engineers building production AI systems and evals.
NVIDIA
★ 3,301skills
Agent Skills for NVIDIA products, install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end. Skill Catalog Product | Description | Skills | AIQ | NVIDIA AI-Q Blueprint - deploy local AI-Q services and run shallow or deep research workflows as agent skills.
Ontos-AI
★ 3,293knowhere
Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.
rag-web-ui
★ 3,289rag-web-ui
RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.
superlinked
★ 3,283sie
Open-source inference server and production cluster for all the models your agent needs.
neomjs
★ 3,272neo
Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.
Snailclimb
★ 3,234interview-guide
基于 Spring Boot 4.1、Java 25、Spring AI 2.0、React、PostgreSQL/pgvector、Redis 和 RustFS 构建的开源 AI 面试平台，支持简历智能分析、模拟面试、语音面试和知识库 RAG。
xpf0000
★ 3,217FlyEnv
All-in-One Native Local Development Environment for Windows, macOS & Linux. Docker alternative for PHP, Node.js, Python and more. Faster alternative to XAMPP, Laragon, MAMP and Laravel Herd with databases, Cron Jobs and runtime management.
qdrant
★ 3,203fastembed
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Filimoa
★ 3,158open-parse
Improved file parsing for LLM’s
decodingai-magazine
★ 3,087second-brain-ai-assistant-course
Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.
amitshekhariitbhu
★ 3,073ai-engineering-interview-questions
Your Cheat Sheet for AI Engineering Interview – Questions and Answers.
swirlai
★ 3,045swirl-search
AI Search & RAG Without Moving Your Data. Get instant answers from your company's knowledge across 100+ apps while keeping data secure. Deploy in minutes, not months.
pinecone-io
★ 3,043examples
Jupyter Notebooks to help you get hands-on with Pinecone vector databases
yilewang
★ 3,014llm-for-zotero
An open-source research agent system for your Zotero library.
pingcap
★ 2,970autoflow
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
oceanbase
★ 2,935seekdb
The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run, and more stable.
FB208
★ 2,934OpenBidKit_Yibiao
This project helps teams deliver faster with open-source tooling and practical workflows.