# AutoGPT

> Build, deploy, and run continuous AI agents from reusable blocks

- Category: Agents & Automation / Agent Frameworks & Builders
- Licence: Polyform-Shield / MIT
- Repository: https://github.com/Significant-Gravitas/AutoGPT
- Website: https://agpt.co
- Canonical page: https://ai-tldr.dev/tools/autogpt/

## In short

AutoGPT is a platform for creating, deploying, and managing continuous AI agents that automate multi-step workflows. It sits in the Agent Frameworks & Builders category of the Agents & Automation tools and is open-source, licensed Polyform-Shield / MIT. To get started: check system requirements.

## Overview

AutoGPT is a platform for creating, deploying, and managing continuous AI agents that automate multi-step workflows. You build an agent by connecting blocks, where each block performs a single action, and chain them together into a workflow that can run on its own and be triggered by external sources.

It's aimed at developers and technical builders who want to run agents themselves. You can self-host the platform with Docker for free, or join the waitlist for the cloud-hosted beta. A low-code Agent Builder, workflow management, deployment controls, and monitoring are included, plus a library of pre-built agents you can run as-is.

As a general agent framework, AutoGPT covers the full lifecycle: design the workflow in the frontend, run it on the AutoGPT Server, and watch its performance through built-in monitoring and analytics.

## What it does

- Block-based agent builder: connect blocks that each perform one action into a full workflow
- Low-code frontend for designing, configuring, and editing agents without deep boilerplate
- AutoGPT Server runs agents continuously and lets them be triggered by external sources
- Marketplace and library of pre-built, ready-to-run agents
- Deployment controls to manage agents from testing through production
- Monitoring and analytics to track agent performance over time

## Getting started

Self-hosting AutoGPT is a Docker-based setup. The quickest path is the official one-line install script, which installs dependencies, configures Docker, and launches a local instance. You'll need Docker, git, Node.js, and npm installed first.

1. Check system requirements

   You need Docker Engine 20.10+, Docker Compose 2.0+, Git 2.30+, and Node.js 16+ with npm 8+. Recommended hardware is 4+ CPU cores, 8GB+ RAM, and at least 10GB of free storage.

2. Run the one-line setup (macOS/Linux)

   This downloads and runs the official install script, which sets up dependencies, configures Docker, and launches your local instance.

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

3. Run the one-line setup (Windows)

   On Windows, use the PowerShell command instead. Windows 10/11 with WSL2 is required.

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

4. Build your first agent

   Once the local instance is running, open the frontend and use the Agent Builder to connect blocks into a workflow, or pick a pre-configured agent from the library. See the official docs for building custom blocks.

## When to use it

- Automating multi-step content workflows, such as reading trending topics and generating short-form videos from them
- Monitoring a source (like a YouTube channel) and transcribing, summarizing, then posting highlights to social media
- Running long-lived agents that operate continuously and respond to external triggers
- Prototyping agent workflows with a low-code block builder before deploying to production