Run This Ai
EN DE

AutoRAG

Agentic RAG platform that automatically optimizes retrieval pipelines so your AI agent can find anything in your documents.

★ 4,963 GitHub MIT ragagentic-ragretrievalknowledge-baseoptimizationpython RAG & Knowledge

Overview

AutoRAG is an open-source RAG (Retrieval-Augmented Generation) platform that goes beyond simple question-answering. It supports advanced RAG techniques — including multi-modal RAG, web search, and agentic RAG — and automatically optimizes your retrieval pipeline through data-driven evaluation. You define the evaluation metrics, and AutoRAG tests hundreds of pipeline combinations to find the best one for your data. It gets smarter the more you use it, making it a practical choice for teams that want production-ready RAG without hand-tuning every component.

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:
  autorag:
    image: autoraghq/autorag:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/autorag:/data

Best VPS for AutoRAG →

Related tools

Guides & articles