Run This Ai
EN DE

GPTMe

Your AI agent in your terminal — writes code, uses the terminal, browses the web, and automates tasks autonomously

★ 4,355 GitHub MIT ai-agentterminalclicode-generationopen-source AI Agents

Overview

GPTMe is an open-source AI agent that lives in your terminal. Unlike typical chatbots or web-based AI tools, GPTMe operates directly in your command line environment with access to local tools: it can write and execute code, use the terminal, browse the web, search files, and manage your development workflow — all autonomously. Built with Python and powered by multiple LLM providers (OpenAI, Anthropic, OpenRouter, llama.cpp), GPTMe gives you a persistent autonomous agent that learns from context and works alongside you. Features include tool orchestration, multi-step reasoning, RAG capabilities, conversation memory, web browsing, code generation and execution, and a web UI for remote access. With 4,300+ stars on GitHub and MIT license, GPTMe is a compelling open-source alternative to proprietary AI coding assistants.

Requirements

Min vCPU
1
Min RAM
1024 MB
Min Disk
10 GB
Rec vCPU
2
Rec RAM
2048 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:
  gptme:
    image: remyxai/gh-gptme-gptme:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/gptme:/data

Best VPS for GPTMe →

Related tools

Guides & articles