RAG 知识库开源项目推荐(120 个)

自托管、可扩展的 AI 对话界面，支持 Ollama 与 OpenAI 兼容 API

构建智能体与 LLM 应用的开发框架

100+ 开源 AI Agent、Agent Skills 与 RAG 应用合集

把代码库与文档变成可查询的知识图谱

为 AI 编程助手提供跨会话持久记忆的压缩系统

开源 RAG 引擎，融合 Agent 能力为 LLM 构建上下文层

把 PDF 和图片转成结构化数据的 OCR 工具包

把任意网站抓取为适合 LLM 的干净 Markdown

Datawhale 出品的从零构建 AI 智能体系统教程

面向 LLM 的提示工程指南，涵盖论文、教程与工具

在内容进入 LLM 前压缩工具输出、日志与 RAG 片段

为 AI Agent 提供持久化记忆层的开源基础设施

本地优先的一体化 AI 应用，与文档对话并运行 AI Agent

基于 Pathway 的无代码实时 RAG 服务，支持多种向量数据库

开源 AI Agent 教材：10 章正文 + 109 个配套实验

构建 LLM 应用的开源数据框架，支持 RAG 与智能体

企业级 AI 低代码平台，一句话生成前后端代码与完整系统

面向 AI 应用的高性能云原生向量数据库

Build resilient agents.

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

自托管、可扩展的 AI 对话界面，支持 Ollama 与 OpenAI 兼容 API

构建智能体与 LLM 应用的开发框架

100+ 开源 AI Agent、Agent Skills 与 RAG 应用合集

把代码库与文档变成可查询的知识图谱

为 AI 编程助手提供跨会话持久记忆的压缩系统

开源 RAG 引擎，融合 Agent 能力为 LLM 构建上下文层

把 PDF 和图片转成结构化数据的 OCR 工具包

把任意网站抓取为适合 LLM 的干净 Markdown

Datawhale 出品的从零构建 AI 智能体系统教程

面向 LLM 的提示工程指南，涵盖论文、教程与工具

在内容进入 LLM 前压缩工具输出、日志与 RAG 片段

为 AI Agent 提供持久化记忆层的开源基础设施

本地优先的一体化 AI 应用，与文档对话并运行 AI Agent

基于 Pathway 的无代码实时 RAG 服务，支持多种向量数据库

开源 AI Agent 教材：10 章正文 + 109 个配套实验

构建 LLM 应用的开源数据框架，支持 RAG 与智能体

企业级 AI 低代码平台，一句话生成前后端代码与完整系统

面向 AI 应用的高性能云原生向量数据库

Build resilient agents.

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models and business rules.

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

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 Llama) RAG and Agent app with langchain

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

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 (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

Vane is an AI-powered answering engine.

A modular graph-based Retrieval-Augmented Generation (RAG) system

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

📚 从零开始构建大模型

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Open Source AI Platform - AI Chat with advanced features that works with every LLM

Python scraper based on AI

Build Real-Time Knowledge Graphs for AI Agents

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

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, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

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, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

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?

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 and CI/CD integration. Used by OpenAI and Anthropic.

An open-source RAG-based tool for chatting with your documents.

50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.

✅（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】

"RAG-Anything: All-in-One RAG Framework"

🔥 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。

🚀 A curated collection of AI engineering resources, roadmaps, tools, and projects covering LLMs, RAG, AI Agents, MCP, fine-tuning, evaluations, and production AI systems.

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.

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

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.

Unified framework for building enterprise RAG pipelines with small, specialized models

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Agent S: an open agentic framework that uses computers like a human

Retrieval and Retrieval-augmented LLMs

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

🧑‍🚀 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.

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

The open source platform for AI-native application development.

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

Everything you need to know to build your own RAG application

Harness LLMs with Multi-Agent Programming

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

Open-source inference server and production cluster for all the models your agent needs.

[KDD'2026] "VideoRAG: Chat with Your Videos"

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

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.

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

All-in-one platform for search, recommendations, RAG, and analytics offered via API

Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.

Comprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview preparation, and coding preparation.

Distributed vector search for AI-native applications

NestJS Helper + AI Chatbot Development

[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"

A community-driven collection of RAG (Retrieval-Augmented Generation) frameworks, projects, and resources. Contribute and explore the evolving RAG ecosystem.

NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.

List of software that allows searching the web with the assistance of AI: https://hf.co/spaces/felladrin/awesome-ai-web-search

Comprehensive guide to learn RAG from basics to advanced.

😎 Awesome list of Retrieval-Augmented Generation (RAG) applications in Generative AI.

Awesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language Models

The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.

面向程序员的大模型全栈学习路线与中文教程

将个人知识、记忆与决策蒸馏为可检查的 AI Agent Twin

本地优先的全栈 AI 创作工作站，覆盖对话、漫画、漫剧、写作与知识学习。

魔搭紫皮书：开源模型应用实战指南

本地优先的二次元陪伴学习应用，支持资料问答与虚拟角色语音交流

免费 24 周 AI 工程自学课程，含 43 个可运行 notebook

基于 DeepSeek Harness 的自托管企业级 Agent 平台

面向 Python 的 AI 智能文档处理框架，支持多 LLM 后端与 OCR

为 AI 智能体构建受治理的权威知识系统

把文档整理成可阅读、可溯源的 Markdown 知识库

面向人文社科的多智能体研究系统，用 DAG 和症候阅读挖掘多元叙事

把 AI 评测结果变成可审查的发布证据与 CI 质量门禁

从零手写企业级 Agent 系统的 32 课双语训练营

为 LLM agent 提供有界、可自纠错的长期记忆层

本地优先的个人知识图谱，把笔记、网页、PDF 和音视频变成可追溯的证据网络。

本地优先的学术研究助手，支持论文搜索、PDF问答与引用导出

修复 PDF 提取文本中的 CJK 形近字，让检索和匹配恢复正常。

用 Jev 与 PageIndex 在长文档中定位答案页

立正公开资料库，为人和 AI 提供可检索、可引用的原文与结构化数据。

不摘要、全保留、带时间戳的个人 AI 长期记忆层

为 AI 编码代理提供跨仓库持久记忆的本地检索工具

面向校园招聘的本地优先求职工作台

开源自托管 AI 业务编排平台，让 AI Agent 安全操作企业系统

ACL 2026 论文 AMA 的官方代码与可复用记忆技能

在选表阶段就按权限过滤 schema 的 text-to-SQL 访问控制

为 OpenAI Codex 提供本地持久记忆，无需托管向量数据库

面向零基础的 Agent、RAG 与大模型图文学习笔记

自托管、可追溯的文档到知识工作台，AI 可选

基于 LangGraph 的 AIOps 告警诊断与修复审批工程

本地优先的混合检索第二大脑，支持 MCP 供 AI 代理调用

安卓 AI 聊天客户端，兼容 SillyTavern 角色卡与预设