LightRAG — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by HKUDS · Agent Tool · ★ 40.0k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is LightRAG safe to install? View the security audit →

About LightRAG

🚀 LightRAG: Simple and Fast Retrieval-Augmented Generation <img src="https://img.shie

doclinggenaigptgraphragknowledge-graphlarge-language-modelsllmmineruragragas

Quick Facts

Stars39,955
Forks5,649
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score61.948305801124/100
Open Issues313
Last Updated2026-10-03
Created2024-10-02
Platformscli, python
Est. Tokens~21k

Compatible Skills

These tools work well together with LightRAG for enhanced workflows:

  • ragflow — semantic(0.44)+complementary+rare_topics+same_lang+similar_pop+shared_platform (74%)
  • langroid — semantic(0.42)+complementary+rare_topics+same_lang+similar_pop+shared_platform (64%)
  • PocketFlow — semantic(0.27)+complementary+rare_topics+same_lang+similar_pop+shared_platform (59%)
  • MemOS — semantic(0.19)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)

LightRAG alternative? Top 6 similar tools

Looking for a LightRAG alternative? If you're comparing LightRAG with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • ragflow by infiniflow · ⭐ 90.9k

    RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with

  • dify by langgenius · ⭐ 157.8k

    Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. De

  • code-review-graph by tirth8205 · ⭐ 31.6k

    Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding too

  • repomix by yamadashy · ⭐ 28.7k

    📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for w

  • ai-guide by liyupi · ⭐ 20.6k

    程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程,分享 OpenClaw 保姆级教程、大模型玩法(DeepSeek / GPT / Gemini / Claude / GLM)、最新 AI 资讯、Pr

  • open-webui by open-webui · ⭐ 153.8k

    User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is LightRAG?

LightRAG is [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation. It is categorized as a Agent Tool with 40.0k GitHub stars.

What programming language is LightRAG written in?

LightRAG is primarily written in Python. It covers topics such as docling, genai, gpt.

How do I install or use LightRAG?

You can find installation instructions and usage details in the LightRAG GitHub repository at github.com/HKUDS/LightRAG. The project has 40.0k stars and 5649 forks, indicating an active community.

What license does LightRAG use?

LightRAG is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to LightRAG?

The top alternatives to LightRAG on Agent Skills Hub include ragflow, dify, code-review-graph. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools