Run This Ai
EN DE

LEANN

RAG on Everything. Index millions of documents on your laptop with 97% storage savings, zero accuracy loss, and complete privacy — no cloud, no telemetry.

★ 12,821 GitHub MIT ragvector-searchlangchainllama-indexollamaoffline-firstmcp RAG & Knowledge

Overview

LEANN is a lightweight vector database that turns any laptop into a private RAG engine. Using graph-based selective recomputation, it computes embeddings on demand instead of storing them, cutting storage by up to 97% without sacrificing accuracy. It ships with native MCP integration, works with LangChain, LlamaIndex, Ollama and Claude Code, and can index your files, emails, chat history and live data — fully offline.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  leann:
    image: https://github.com/StarTrail-org/LEANN/blob/main/docker/Dockerfile
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/leann:/data

Best VPS for LEANN →

Related tools

Guides & articles