AutoGPT: Build, Deploy, and Run AI Agents

 
 

Deutsch |
Español |
français |
日本語 |
한국어 |
Português |
Русский |
中文

AutoGPT is a powerful platform that allows you to create, deploy, and manage continuous AI agents that automate complex workflows.

Hosting Options

• Download to self-host (Free!)
• Join the Waitlist for the cloud-hosted beta (Closed Beta - Public release Coming Soon!)

How to Self-Host the AutoGPT Platform

[!NOTE]
Setting up and hosting the AutoGPT Platform yourself is a technical process.
If you'd rather something that just works, we recommend joining the waitlist for the cloud-hosted beta.

System Requirements

Before proceeding with the installation, ensure your system meets the following requirements:

Hardware Requirements

• CPU: 4+ cores recommended
• RAM: Minimum 8GB, 16GB recommended
• Storage: At least 10GB of free space

Software Requirements

• Operating Systems:
  • Linux (Ubuntu 20.04 or newer recommended)
  • macOS (10.15 or newer)
  • Windows 10/11 with WSL2
• Required Software (with minimum versions):
  • Docker Engine (20.10.0 or newer)
  • Docker Compose (2.0.0 or newer)
  • Git (2.30 or newer)
  • Node.js (16.x or newer)
  • npm (8.x or newer)
  • VSCode (1.60 or newer) or any modern code editor

Network Requirements

• Stable internet connection
• Access to required ports (will be configured in Docker)
• Ability to make outbound HTTPS connections

Updated Setup Instructions:

We've moved to a fully maintained and regularly updated documentation site.

👉 Follow the official self-hosting guide here

This tutorial assumes you have Docker, VSCode, git and npm installed.

---

⚡ Quick Setup with One-Line Script (Recommended for Local Hosting)

Skip the manual steps and get started in minutes using our automatic setup script.

For macOS/Linux:

curl -fsSL https://setup.agpt.co/install.sh -o install.sh && bash install.sh

For Windows (PowerShell):

powershell -c "iwr https://setup.agpt.co/install.bat -o install.bat; ./install.bat"

This will install dependencies, configure Docker, and launch your local instance — all in one go.

🧱 AutoGPT Frontend

The AutoGPT frontend is where users interact with our powerful AI automation platform. It offers multiple ways to engage with and leverage our AI agents. This is the interface where you'll bring your AI automation ideas to life:

Agent Builder: For those who want to customize, our intuitive, low-code interface allows you to design and configure your own AI agents.

Workflow Management: Build, modify, and optimize your automation workflows with ease. You build your agent by connecting blocks, where each block performs a single action.

Deployment Controls: Manage the lifecycle of your agents, from testing to production.

Ready-to-Use Agents: Don't want to build? Simply select from our library of pre-configured agents and put them to work immediately.

Agent Interaction: Whether you've built your own or are using pre-configured agents, easily run and interact with them through our user-friendly interface.

Monitoring and Analytics: Keep track of your agents' performance and gain insights to continually improve your automation processes.

Read this guide to learn how to build your own custom blocks.

💽 AutoGPT Server

The AutoGPT Server is the powerhouse of our platform This is where your agents run. Once deployed, agents can be triggered by external sources and can operate continuously. It contains all the essential components that make AutoGPT run smoothly.

Source Code: The core logic that drives our agents and automation processes.

Infrastructure: Robust systems that ensure reliable and scalable performance.

Marketplace: A comprehensive marketplace where you can find and deploy a wide range of pre-built agents.

🐙 Example Agents

Here are two e