// agents · HKUDS/LightRAG

LightRAG

LightRAG é um projeto de agentes de IA de código aberto de HKUDS (HKUDS/LightRAG no GitHub). Tem 40.014 estrelas no GitHub e 5.668 forks, é publicado sob a licença MIT e foi atualizado pela última vez no GitHub em 3 de outubro de 2026.

Simple, fast retrieval-augmented generation with graph smarts.

★ 40,0 mil estrelas⑂ 5,7 mil forksMITatualizado out 2026

Ver no GitHub ↗

▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.

// dados do projeto

Dados do projeto

Repositório: HKUDS/LightRAG
Estrelas no GitHub: 40.014
Forks: 5.668
Licença: MIT
Última atualização no GitHub: 3 de outubro de 2026
Categoria: Agentes de IA
Tipo de ficha: Guia de instalação completo

// como funciona

Como funciona

Start with a use case
Pick one concrete task so you can judge whether the project fits.
Fetch the source
Clone the repo and check the prerequisites listed in the README.
Set up the environment
Install what it needs and configure credentials or model access.
Try the sample workflow
Run a minimal example end to end before wiring it into your stack.

// recursos

Por que as pessoas gostam tanto

Graph-enhanced RAG

Uses knowledge-graph structure to organize retrieval.

Research-backed

Presented at EMNLP 2025 with an accompanying paper.

Simple and fast

Positioned as a lean alternative to heavyweight RAG stacks.

Python-native

Hackable Python codebase.

MIT licensed

Permissive licensing.

Large community

Over 5,600 forks.

// execute você mesmo

Execute você mesmo

Step 1 — Clone the repo
Download the source and move into the project folder.
```
git clone https://github.com/HKUDS/LightRAG.git
cd LightRAG
```
Step 2 — Install dependencies
Set up a virtual environment and install requirements.
```
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
```
Step 3 — Run an example
Configure your LLM/embedding keys and run the quickstart.
```
# see README for the exact example path
python examples/quickstart.py
```

// casos de uso

O que você pode criar

Prototype a RAG system with graph-structured retrieval.
Reproduce or extend the EMNLP 2025 paper's approach.
Compare graph RAG against naive chunk retrieval.
Teach a course module on modern retrieval techniques.

// perguntas frequentes

Perguntas frequentes

Who maintains LightRAG?

It is maintained by HKUDS at HKUDS/LightRAG, with 5,668 forks. The project page links to the EMNLP 2025 paper for background.

Is LightRAG free to use?

Yes. It is released under the MIT license, which permits commercial use, modification, and redistribution. Read the LICENSE file for the exact terms.

Do I need a paid API to use it?

You will need an LLM and embedding provider for generation and embeddings; the framework itself is free.

How does it compare to other RAG frameworks?

Compare on retrieval quality and simplicity for your corpus — its selling point is lean, graph-enhanced retrieval.

How do I get started?

Os outros projetos de Agentes de IA com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se LightRAG não for o ideal para você.

openclaw★ 391,6 mil
A personal AI that really does things — on any OS, with your data staying yours.
superpowers★ 294,9 mil
An agentic skills framework & software development methodology that works.
ECC★ 275,2 mil
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
hermes-agent★ 252,0 mil
The agent that grows with you — a Python framework for adaptive AI agents.
deepseek-harness★ 245,5 mil
DeepSeek's plugin-based agent harness where everything is a plugin.

// mais em agents

Mais em Agentes de IA

Projetos de Agentes de IA próximos no catálogo, os mais próximos em estrelas de LightRAG: continue explorando dos dois lados dele.

ToolJet★ 41,0 mil
Open-source foundation of ToolJet AI - the enterprise app generation platform for internal tools, dashboards, business applications, workflows and AI agents.…
OpenViking★ 39,4 mil
A self-evolving context database unifying agent memory, RAG, and skills.
AstrBot★ 41,3 mil
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
UI-TARS-desktop★ 39,2 mil
ByteDance's open-source multimodal AI agent stack: GUI agents that see and operate real desktops
openhuman★ 41,7 mil
A fast, local-first open-source agent harness written in Rust, with desktop, browser and terminal apps
dspy★ 38,6 mil
Program language models with code and compilers — not fragile prompts.

Baixe o LightRAG

Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.

Ver no GitHub ↗← Mais ferramentas de Agentes de IA