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

553–576 of 642
LnYo-Cly

ai4j

★ 432

Java 8+ agentic SDK: unified LLM access (OpenAI/Anthropic/DashScope/Doubao/DeepSeek...), Tool Calling, MCP, RAG, Agent Runtime, and a built-in Coding Agent CLI/TUI/ACP.

Java
Earth-OL-Player

ai_learn_project

★ 431

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
vintasoftware

django-ai-assistant

★ 431

Integrate AI Assistants with Django to build intelligent applications

Python
★ 430

Redis Vector Library. The AI-native Python client for Redis.

Python
★ 425

《动手学SpringAI》包含SSE流/Agent智能体/知识图谱RAG/FunctionCall/历史消息/图片生成/图片理解/Embedding/VectorDatabase/RAG

Java
ageerle

ruoyi-web

★ 423

RuoYi-AI user frontend for AI conversations, agent interactions, and knowledge-base Q&A.

Vue
gyunggyung

AGI-Papers

★ 421

A curated archive of breakthroughs in Agents, Architecture, Training, RAG, and On-Device AI.

Laxcorp-Research

project-raven

★ 421

Open-source AI meeting copilot - real-time transcription, echo cancellation, and AI assistance. Captures system audio + mic, cancels echo via WebRTC AEC3, transcribes with Deepgram, and gives you Claude/OpenAI help during meetings. Runs locally on macOS and Windows.

TypeScript
unitagain

WenShape

★ 420

WenShape文枢(原NOVIX写作):深度上下文感知的智能体小说创作系统/A Deep Context-Aware Agent-Based Novel Creation System

Python
★ 419

📊 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
GizClaw

flowcraft

★ 416

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

Go
datawhalechina

easy-vecdb

★ 413

📚 从零开始的向量数据库原理与实践教程，在线阅读地址：https://easy-vecdb.datawhale.cc/

Jupyter Notebook
★ 412

RAG evaluation without the need for "golden answers"

Python
treygrainger

ai-powered-search

★ 411

The codebase for the book "AI-Powered Search" (Manning Publications, 2025) and associated "AI-Powered Search: Modern Retrieval for Humans & Agents" Maven course

Jupyter Notebook
★ 410

A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (+RAG, Agents). Monthly Updates.

Python
Lyellr88

marm-memory

★ 409

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
★ 409

Cut LLM costs by up to 80% and unlock sub-millisecond responses with intelligent semantic caching.A drop-in, provider-agnostic LLM proxy written in Go with sub-millisecond response

Go
★ 408

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

Jupyter Notebook
Mintplex-Labs

anythingllm-docs

★ 406

Documentation of AnythingLLM by Mintplex Labs Inc.

MDX
★ 405

Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.

TypeScript
★ 404

Serverless Modal + FastAPI + React + ColPali + Qdrant + GPT4o Vision RAG (V-RAG) Demo

TypeScript
★ 403

Veldra — talk an agent into existence, then watch it grow. A self-hostable, local-first agent platform: describe what you need in plain language and it compiles a working agent tools, MCP, RAG, teams. The more you use it, the better it gets agents learn from your feedback and reshape as you talk.

Python
★ 394

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

Python