Run This Ai
EN DE

LightRAG

Simple and Fast Retrieval-Augmented Generation

★ 37,107 GitHub MIT ragknowledge-graphretrieval-augmented-generationllmembeddingspython RAG & Knowledge

Overview

LightRAG is a high-performance, lightweight RAG framework with 37k+ stars on GitHub. Published at EMNLP 2025, it provides simple, fast retrieval-augmented generation with graph-based knowledge indexing, dual-level retrieval, and a built-in WebUI. Perfect for building knowledge bases, document Q&A, and AI-powered search.

Requirements

Min vCPU
1
Min RAM
2048 MB
Min Disk
10 GB
Rec vCPU
2
Rec RAM
4096 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 2

2 vCPU · 8192 MB · 100 GB

$6.99
View plan

Hostinger · KVM 2

2 vCPU · 8192 MB · 100 GB

$6.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  lightrag:
    image: ghcr.io/hkuds/lightrag:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/lightrag:/data

Best VPS for LightRAG →

Related tools

Guides & articles