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

385–408 of 596

bartolli

codanna

★ 742

Local code intelligence MCP server and CLI for AI coding agents

Rust

opea-project

GenAIExamples

★ 742

Generative AI Examples is a collection of GenAI examples such as ChatQnA, Copilot, which illustrate the pipeline capabilities of the Open Platform for Enterprise AI (OPEA) project.

Shell

iamzulx

crypto-rag

★ 738

Asisten crypto berbahasa Indonesia: RAG pengetahuan 267 topik + data pasar realtime (6 bursa, WebSocket, derivatif, on-chain, TVL, DeFi) + tool-calling agent + LLM synthesis

Python

w8123

EnterpriseAgentFramework

★ 737

ReachAI企业级智能体开发平台：快速、安全完成已有业务系统智能化改造，让 AI 在 OA、ERP、CRM 等原系统中查数据、填表单、办业务。ReachAI: Quickly and securely bring AI to existing enterprise systems, enabling AI to query data, fill out forms, and execute business tasks directly within OA, ERP, CRM, and other business applications.

Java

ghimiresunil

LLM-PowerHouse-A-Curated-Guide-for-Large-Language-Models-with-Custom-Training-and-Inferencing

★ 732

LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.

Jupyter Notebook

agentic-box

memora

★ 726

Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.

Python

symgraph

GhidrAssist

★ 723

An LLM extension for Ghidra to enable AI assistance in RE.

Java

emarco177

langgraph-course

★ 722

Hands-on LangGraph course repo for building production-grade LLM agents with Agentic RAG, ReAct, and reflection workflows.

nuclia

nucliadb

★ 721

NucliaDB, The AI Search database for RAG

Python

prompt-security

ps-fuzz

★ 710

Make your GenAI Apps Safe & Secure :rocket: Test & harden your system prompt

Python

liliu-z

stashbase

★ 694

Turn your local files into a Wiki for your agents. Open-source and local-first.

TypeScript

swarmclawai

swarmvault

★ 692

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.

TypeScript

agarwalvishal

claude-chat-exporter

★ 690

One-click, privacy-first exporter for Claude.ai chats — clean Markdown with artifacts and attachments, ready for Obsidian and RAG.

JavaScript

davidmigloz

langchain_dart

★ 687

Build LLM-powered Dart/Flutter applications.

Dart

Junvate

LLM-Algorithm-Intern-Guide

★ 684

🚀 2026届大模型算法岗实习面经 | 包含 DeepSeek/Qwen 技术报告解析、手撕 PPO/RoPE/Transformer、RLHF 核心与八股文 | 持续更新中...

DataScienceUIBK

Rankify

★ 683

🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved benchmark datasets and supports 7+ retrieval techniques, 24+ state-of-the-art Reranking models, and multiple RAG methods.

Python

TIGER-AI-Lab

VLM2Vec

★ 683

This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]

Python

usemoss

moss

★ 681

The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.

Python

xynehq

xyne

★ 681

AI-first Search & Answer Engine for work. Open-source alternative to Glean.

TypeScript

JuliusBrussee

cavemem

★ 680

Frozen — cross-agent persistent memory for coding assistants. Still works; the compressed-memory core now ships inside JuliusBrussee/caveman.

TypeScript

SensAI-PT

RAGMeUp

★ 680

Generic rag framework to apply the power of LLMs on any given dataset

Python

Bessouat40

RAGLight

★ 673

RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.

Python

framerslab

agentos

★ 662

TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.

TypeScript

MatrixAges

polywise

★ 659

The open source agentic content system to make your contents alive. Self-hosted on any platform. ◑

TypeScript