AI channel
RAG

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

529–552 of 596
Earth-OL-Player

ai_learn_project

394

一站式Agent开发学习平台: Agent开发学习路线资料、智能刷题、面经题库

Java
394

FoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready.

Python
391

📊 电商数仓智能问数 AI Agent,最适合用于系统学习 LangGraph 的实战项目:基于 LangGraph、FastAPI、Qdrant、Elasticsearch、MySQL 与 React,完整实现元数据知识库、混合检索、自然语言生成 NL2SQL 生成校验、SQL 执行与流式查询展示。前后端完整代码全栈可跑,Docker 环境一键部署,配套 ai-agents-from-zero 免费教程与章节代码分支。适合系统学习大模型应用、数据分析 Agent 和企业级 AI 工程落地。

Python
wangtunan

blog

391

:memo: 记录个人博客,见证成长之路 https://wangtunan.github.io/blog/

Shell
390

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

Python
buildingjoshbetter

TrueMemory

380

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.

Python
Lyellr88

marm-memory

380

Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.

Python
spitfireuptown

datalinkx

380

🔥🔥DatalinkX异构数据源之间的数据同步系统,支持海量数据的增量或全量同步,同时支持HTTP、Oracle、MySQL、ES等数据源之间的数据流转,支持中间transform算子如SQL算子、大模型算子,底层依赖Flink、Seatunnel引擎,提供流转任务管理、任务级联配置、任务日志采集等功能🔥🔥

Java
379

一个本地优先的AI知识库系统(RAG),用于把本地文档接入辅导搜索与大模型对话流程。目前支持md、txt、pdf(文本)、xlsx、cvs类型。支持mcp服务

Go
mezmo

aura

378

AURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on production infrastructure.

Rust
Socialpranker

deepdive

378

Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation verification. 105 blocks, 29 channels, 460+ stat sources, 47 APIs, 1072 verified endpoints.

Python
mrmps

pdf2md

376

Browser based tool to convert PDFs to Markdown

TypeScript
376

AI 课程笔记:langchain / langgraph / python / vibe coding

Jupyter Notebook
mine-ai-xyz

mine-ai

375

Open-source reference implementations for AI-enabled payment security, blockchain fraud detection, and AML/CFT compliance reasoning.

Python
youngyangyang04

llm-master

375

大模型(LLM)全栈学习路线与中文教程🔥:覆盖 Prompt Engineering、RAG、AI Agent、MCP、微调、模型部署、Transformer、AI 编程与大厂面试,从入门到生产实践。

labsai

EDDI

374

Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.

Java
370

Program that lets you ask questions about your documents, audio, and video files.

Python
iLearn-Lab

NovelClaw

370

Dynamic-memory-first collaborative AI framework for long-form story generation, chapter planning, and coherent narrative writing

Python
feyninc

chonkiejs

368

🦛 CHONK your texts with Chonkie ✨ Type-friendly, light-weight, fast and super-simple chunking library

TypeScript

基于 LangChain/LangGraph 的 ReAct Agent ,结合 RAG、工具调用与 Streamlit 界面,面向智能客服与报告生成场景。

Python
ModelEngine-Group

DataMate

368

DataMate is an enterprise-level data processing platform designed for model fine-tuning and RAG retrieval.

TypeScript
jzjzzzzzzz

agent-me

365

Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.

Python
microsoft

iq-series

365

The IQ Series is a hands-on learning experience for Microsoft IQ: Microsoft's unified intelligence layer for the enterprise, spanning Foundry IQ, Work IQ, and Fabric IQ. The series includes video episodes, Jupyter notebooks, and Azure deployment templates.

Jupyter Notebook
361

Claude Code skill for OWASP security best practices (2025-2026). Includes Top 10:2025, ASVS 5.0, Agentic AI security, and 20+ language-specific security quirks.