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

409–432 of 596

lewislulu

llm-wiki-skill

★ 656

Karpathy-style LLM knowledge base Agent Skill for OpenClaw/Codex. Experimental — will iterate over time.

TypeScript

zavora-ai

adk-rust

★ 651

Rust Agent Development Kit (ADK-Rust): Build AI agents in Rust with modular components for models, tools, memory, realtime voice, and more. ADK-Rust is a flexible framework for developing AI agents with simplicity and power. Model-agnostic, deployment-agnostic, optimized for frontier AI models. Includes support for real-time voice agents.

Rust

chrisryugj

Docufinder

★ 648

Anything — 파일 이름이 아니라 본문으로 찾는 문서 검색기. HWP·PDF·Office 전문 검색을 오프라인으로. Windows·macOS | Offline content search across Korean documents (HWP, PDF, Office). Windows and macOS

Rust

lofcz

LLMTornado

★ 641

The .NET library to build AI agents with 30+ built-in connectors.

henrydaum

second-brain

★ 640

Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.

Python

QmiAI

Qmedia

★ 636

An open-source AI content search engine designed specifically for content creators. Supports extraction of text, images, and short videos. Allows full local deployment (web app, RAG server, LLM server). Supports multi-modal RAG content Q&A.

TypeScript

java-up-up

nexus-agent

★ 634

企业级 AI 智能体 Agent 平台，覆盖智能对话、文档知识问答、联网搜索、RAG 检索、MCP 工具协议、Skills 扩展等完整能力。三层执行器体系、双通道混合检索、组合式切块引擎、会话记忆管理、全链路可观测，每个环节都经过深度设计和工程化打磨。

Java

calmrocks

ai-engineer-notebooks

★ 633

Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scratch, tool design, guardrails, MCP, Skills), fine-tuning vs LoRA, prompt-injection/security, LLMOps, and customer craft. Runs on the free Groq API.

Jupyter Notebook

johnsonhk88

AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction

★ 628

AI Bank Statement Document Automation By LLM model and Personal Finanical Analysis

Jupyter Notebook

OtterMind

Nubase

★ 628

🔥🔥🔥 Turn AI-written code into real apps. Nubase is an open-source, AI-native backend platform for AI Coding, agentic applications, and modern product teams: Memory, Database, Storage, and Auth in one self-hostable service.

Java

GD4AI

obsidian-llm-wiki

★ 627

Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.

TypeScript

samvallad33

vestige

★ 624

Vestige enhances agents by deterministic root-cause retrieval that reaches backward through time to find the quiet change, decision, or service that caused today’s failure, not the lookalike.

Rust

Snailclimb

AIGuide

★ 621

AI 应用开发、AI 编程实战与面试指南，涵盖 LLM、Agent、RAG、MCP、Claude Code、Codex 等核心技术与工程实践。

Ai00-X

ai00_server

★ 620

The all-in-one RWKV runtime box with embed, RAG, AI agents, and more.

Rust

Decade-qiu

CookHero

★ 616

CookHero是一个基于 LLM + RAG + Agent + 多模态的智能饮食与烹饪管理平台，支持智能菜谱查询、个性化饮食计划、AI 饮食记录、营养分析、Web 搜索增强，以及可扩展的 ReAct Agent / Subagent 工具体系，帮助厨房新手轻松成为“烹饪英雄”。

Python

tgoai

tgo

★ 613

Open-source AI Agent Customer Service Platform. Build AI agent teams with LLM orchestration, RAG knowledge base, multi-channel support, and human collaboration.

TypeScript

aryn-ai

sycamore

★ 608

🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.

Python

ggozad

haiku.rag

★ 608

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

Python

benmaster82

Kwipu

★ 607

Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.

Python

tetherto

qvac

★ 604

Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS.

TypeScript