Top 100 RAG Repositories
Ranking
| Ranking | Project Name | Stars | Forks | Language | Open Issues | Description | Last Commit |
|---|---|---|---|---|---|---|---|
| 1 | dify | 148,343 | 23,381 | TypeScript | 272 | Production-ready platform for agentic workflow development. | 2026-07-10 |
| 2 | open-webui | 144,890 | 20,966 | Python | 230 | User-friendly AI Interface (Supports Ollama, OpenAI API, ...) | 2026-07-09 |
| 3 | langchain | 141,421 | 23,501 | Python | 351 | The agent engineering platform. | 2026-07-10 |
| 4 | awesome-llm-apps | 117,117 | 17,413 | Python | 0 | 100+ AI Agent & RAG apps you can actually run — clone, customize, ship. | 2026-07-10 |
| 5 | claude-mem | 86,634 | 7,487 | JavaScript | 133 | Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Cla... | 2026-07-09 |
| 6 | PaddleOCR | 85,132 | 10,993 | Python | 158 | Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages. | 2026-06-26 |
| 7 | ragflow | 84,713 | 9,883 | Go | 1981 | RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs | 2026-07-10 |
| 8 | graphify | 81,350 | 8,008 | Python | 208 | AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable... | 2026-07-10 |
| 9 | Prompt-Engineering-Guide | 76,326 | 8,355 | MDX | 178 | 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents. | 2026-03-11 |
| 10 | hello-agents | 65,185 | 8,079 | Python | 75 | 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程 | 2026-07-06 |
| 11 | ruflo | 63,734 | 7,523 | TypeScript | 499 | 🌊 The leading agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, R... | 2026-07-09 |
| 12 | anything-llm | 63,020 | 6,889 | JavaScript | 300 | Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience | 2026-07-09 |
| 13 | pathway | 62,698 | 1,668 | Python | 30 | Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG. | 2026-07-09 |
| 14 | mem0 | 60,503 | 7,029 | Python | 154 | Universal memory layer for AI Agents | 2026-07-09 |
| 15 | llm-app | 59,081 | 1,430 | Jupyter Notebook | 6 | Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, a... | 2026-07-05 |
| 16 | headroom | 58,197 | 4,298 | Python | 252 | Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server. | 2026-07-10 |
| 17 | private-gpt | 57,326 | 7,599 | Python | 2 | Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server. | 2026-07-09 |
| 18 | Flowise | 54,475 | 24,698 | TypeScript | 684 | Build AI Agents, Visually | 2026-07-06 |
| 19 | llama_index | 50,751 | 7,720 | Python | 192 | LlamaIndex is the leading document agent and OCR platform | 2026-07-08 |
| 20 | JeecgBoot | 46,989 | 16,081 | Java | 33 | 【低代码迈入 v2.0】AI低代码平台，AI Skills 一句话生成整个系统；一键生成前后端代码甚至整个模块。 AI Skills 一句话画流程、设计表单、生成报表、大屏。内置 AI应用平台涵盖：AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领AI低代码「Skills 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，解决 Java 项目 90% 重复工作，提高... | 2026-07-09 |
| 21 | milvus | 45,158 | 4,111 | Go | 754 | Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search | 2026-07-10 |
| 22 | GitNexus | 43,923 | 4,884 | TypeScript | 222 | GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local)... | 2026-07-09 |
| 23 | minds | 39,386 | 6,220 | Makefile | 1 | Delegate anything. It comes back done. | 2026-07-09 |
| 24 | quivr | 39,191 | 3,720 | Python | 9 | Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore:... | 2025-07-09 |
| 25 | Langchain-Chatchat | 38,277 | 6,221 | Python | 6 | Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Ll... | 2025-11-10 |
| 26 | LightRAG | 37,518 | 5,285 | Python | 199 | [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation" | 2026-07-09 |
| 27 | langgraph | 36,921 | 6,197 | Python | 382 | Build resilient agents. | 2026-07-10 |
| 28 | ai-engineering-hub | 36,418 | 6,036 | Jupyter Notebook | 22 | In-depth tutorials on LLMs, RAGs and real-world AI agent applications. | 2026-06-08 |
| 29 | Vane | 35,616 | 3,918 | TypeScript | 221 | Vane is an AI-powered answering engine. | 2026-04-11 |
| 30 | khoj | 35,598 | 2,297 | Python | 96 | Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI ... | 2026-06-24 |
| 31 | graphrag | 34,321 | 3,628 | Python | 13 | A modular graph-based Retrieval-Augmented Generation (RAG) system | 2026-07-08 |
| 32 | PageIndex | 33,907 | 2,967 | Python | 66 | 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG | 2026-07-10 |
| 33 | happy-llm | 31,933 | 3,030 | Jupyter Notebook | 52 | 📚 从零开始构建大模型 | 2026-05-06 |
| 34 | onyx | 30,795 | 4,234 | Python | 137 | Open Source AI Platform - AI Chat with advanced features that works with every LLM | 2026-07-10 |
| 35 | sim | 28,981 | 3,690 | TypeScript | 106 | Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce. | 2026-07-10 |
| 36 | FastGPT | 28,891 | 7,210 | TypeScript | 142 | FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letti... | 2026-07-09 |
| 37 | graphiti | 28,557 | 2,876 | Python | 255 | Build Real-Time Knowledge Graphs for AI Agents | 2026-07-09 |
| 38 | RAG_Techniques | 28,437 | 3,465 | Jupyter Notebook | 8 | This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial. | 2026-07-04 |
| 39 | Scrapegraph-ai | 28,230 | 2,724 | Python | 0 | Python scraper based on AI | 2026-07-08 |
| 40 | opendataloader-pdf | 26,859 | 2,550 | Java | 54 | PDF Parser for AI-ready data. Automate PDF accessibility. Open-source. | 2026-07-10 |
| 41 | OpenViking | 26,496 | 2,069 | Python | 84 | Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | 2026-07-09 |
| 42 | haystack | 25,859 | 2,908 | MDX | 72 | Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, m... | 2026-07-09 |
| 43 | kotaemon | 25,531 | 2,124 | Python | 215 | An open-source RAG-based tool for chatting with your documents. | 2026-06-09 |
| 44 | DeepTutor | 25,427 | 3,463 | Python | 31 | DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/. | 2026-07-09 |
| 45 | crawlee | 24,624 | 1,532 | TypeScript | 129 | Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and o... | 2026-07-09 |
| 46 | 12-factor-agents | 24,019 | 1,834 | TypeScript | 13 | What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? | 2025-09-21 |
| 47 | awesome-n8n-templates | 23,771 | 6,238 | - | 8 | 280+ free n8n automation templates — ready-to-use workflows for Gmail, Telegram, Slack, Discord, WhatsApp, Google Drive, Notion, OpenAI, and more. AI agents, RAG chatbots, email automation, social m... | 2026-07-06 |
| 48 | vanna | 23,757 | 2,445 | Python | 226 | 🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄. | 2026-02-02 |
| 49 | pandas-ai | 23,638 | 2,335 | Python | 6 | Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG. | 2025-10-28 |
| 50 | promptfoo | 23,097 | 2,062 | TypeScript | 95 | Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line ... | 2026-07-10 |
| 51 | GenAI_Agents | 23,055 | 3,876 | Jupyter Notebook | 3 | 50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems. | 2026-07-04 |
| 52 | CV | 22,535 | 2,553 | Jupyter Notebook | 22 | ✅（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】 | 2026-06-30 |
| 53 | RAG-Anything | 22,107 | 2,572 | Python | 98 | "RAG-Anything: All-in-One RAG Framework" | 2026-07-09 |
| 54 | MaxKB | 22,020 | 2,991 | Python | 56 | 🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。 | 2026-07-10 |
| 55 | coze-studio | 21,138 | 3,076 | TypeScript | 482 | An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation. | 2026-04-20 |
| 56 | agents-towards-production | 20,949 | 2,785 | Jupyter Notebook | 6 | End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment. | 2026-07-04 |
| 57 | opik | 20,506 | 1,595 | Python | 89 | Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards. | 2026-07-10 |
| 58 | DB-GPT | 19,434 | 2,811 | Python | 370 | open-source agentic AI data assistant for the next generation of AI + Data products. | 2026-07-09 |
| 59 | eliza | 18,718 | 5,580 | TypeScript | 171 | Open source agentic operating system | 2026-07-10 |
| 60 | llama-cookbook | 18,399 | 2,750 | Jupyter Notebook | 19 | Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model f... | 2026-05-19 |
| 61 | WeKnora | 18,050 | 2,466 | Go | 242 | Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. | 2026-07-09 |
| 62 | DocsGPT | 17,975 | 2,072 | Python | 23 | Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents. | 2026-07-09 |
| 63 | ai-guide | 17,067 | 1,924 | JavaScript | 0 | 程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Prompt 提示词大全、AI 知识百科（Agent Skills / RAG / MCP / A2A）、AI 编程教程（Harness Engineering）、AI 工具用法（Cu... | 2026-07-01 |
| 64 | LangBot | 16,807 | 1,486 | Python | 105 | Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integr... | 2026-07-09 |
| 65 | Qwen-Agent | 16,697 | 1,664 | Python | 419 | Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc. | 2026-03-04 |
| 66 | RagaAI-Catalyst | 16,143 | 3,578 | Python | 17 | Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced anal... | 2026-02-11 |
| 67 | WrenAI | 15,773 | 1,807 | Python | 271 | GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data s... | 2026-07-10 |
| 68 | memvid | 15,739 | 1,360 | Rust | 9 | Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory. | 2026-05-27 |
| 69 | Memori | 15,555 | 2,793 | Python | 10 | Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori wo... | 2026-06-15 |
| 70 | SurfSense | 15,214 | 1,460 | Python | 106 | NotebookLM for Competitive Intelligence. Give your AI agents Competitive Intelligence. Join our Discord: https://discord.gg/ejRNvftDp9 | 2026-07-09 |
| 71 | llmware | 14,816 | 2,909 | Python | 71 | Unified framework for building enterprise RAG pipelines with small, specialized models | 2026-05-17 |
| 72 | ragas | 14,770 | 1,550 | Python | 327 | Supercharge Your LLM Application Evaluations 🚀 | 2026-02-24 |
| 73 | zvec | 14,658 | 906 | C++ | 33 | A lightweight, lightning-fast, in-process vector database | 2026-07-10 |
| 74 | easy-dataset | 14,623 | 1,493 | JavaScript | 113 | A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval | 2026-05-01 |
| 75 | llm_wiki | 14,140 | 1,689 | TypeScript | 162 | LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch e... | 2026-07-08 |
| 76 | llm-universe | 13,444 | 1,373 | Jupyter Notebook | 10 | 本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/ | 2026-02-24 |
| 77 | awesome-ai-apps | 13,048 | 1,672 | Python | 46 | A collection of projects showcasing RAG, agents, workflows, and other AI use cases | 2026-06-28 |
| 78 | txtai | 12,712 | 843 | Python | 9 | 💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows | 2026-07-02 |
| 79 | LEANN | 12,664 | 1,141 | Python | 36 | [MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device. | 2026-07-03 |
| 80 | turbovec | 12,626 | 1,116 | Python | 12 | A vector index built on TurboQuant, written in Rust with Python bindings | 2026-06-10 |
| 81 | langchain4j | 12,569 | 2,361 | Java | 587 | LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing too... | 2026-07-09 |
| 82 | note-gen | 12,275 | 925 | TypeScript | 146 | A cross-platform Markdown AI note-taking software. | 2026-07-10 |
| 83 | claude-context | 12,101 | 896 | TypeScript | 72 | Code search MCP for Claude Code. Make entire codebase the context for any coding agent. | 2026-06-22 |
| 84 | bisheng | 11,507 | 1,879 | TypeScript | 107 | BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SF... | 2026-07-10 |
| 85 | EverOS | 10,690 | 849 | Python | 34 | One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows. | 2026-07-08 |
| 86 | cocoindex | 10,654 | 826 | Rust | 46 | Incremental engine for long horizon agents 🌟 Star if you like it! | 2026-07-09 |
| 87 | orama | 10,471 | 398 | TypeScript | 17 | 🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb. | 2026-07-03 |
| 88 | aichat | 10,223 | 707 | Rust | 43 | 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. | 2026-02-23 |
| 89 | MemOS | 10,152 | 925 | TypeScript | 63 | Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings | 2026-07-09 |
| 90 | voltagent | 10,004 | 1,039 | TypeScript | 30 | AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework | 2026-07-10 |
| 91 | all-in-rag | 9,374 | 4,673 | Python | 13 | 🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/ | 2026-06-05 |
| 92 | garden-skills | 9,329 | 1,246 | CSS | 6 | ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more. | 2026-06-10 |
| 93 | crawlee-python | 9,291 | 769 | Python | 75 | Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works... | 2026-07-10 |
| 94 | deeplake | 9,202 | 721 | C++ | 54 | Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training. | 2026-05-21 |
| 95 | KAG | 8,883 | 693 | Python | 163 | KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge base... | 2026-01-28 |
| 96 | paper-qa | 8,843 | 887 | Python | 134 | High accuracy RAG for answering questions from scientific documents with citations | 2026-06-29 |
| 97 | rag-from-scratch | 8,821 | 2,111 | Jupyter Notebook | 24 | 2025-06-26 | |
| 98 | awesome-LLM-resources | 8,661 | 921 | - | 0 | 🧑🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources. | 2026-07-09 |
| 99 | xberg | 8,605 | 513 | Rust | 14 | A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Python... | 2026-07-10 |
| 100 | reor | 8,564 | 528 | JavaScript | 113 | Private & local AI personal knowledge management app for high entropy people. | 2025-05-13 |