Skip to content

Getting Started with AutoGPT: Self-Hosting Guide

This tutorial will walk you through the process of setting up AutoGPT locally on your machine.

Introduction

This guide will help you setup the server and builder for the project.

We also offer this in video format. You can check it out here.

Warning

DO NOT FOLLOW ANY OUTSIDE TUTORIALS AS THEY WILL LIKELY BE OUT OF DATE

Prerequisites

To setup the server, you need to have the following installed:

Checking if you have Node.js & NPM installed

We use Node.js to run our frontend application.

If you need assistance installing Node.js: https://nodejs.org/en/download/

NPM is included with Node.js, but if you need assistance installing NPM: https://docs.npmjs.com/downloading-and-installing-node-js-and-npm

You can check if you have Node.js & NPM installed by running the following command:

node -v
npm -v

Once you have Node.js installed, you can proceed to the next step.

Checking if you have Docker & Docker Compose installed

Docker containerizes applications, while Docker Compose orchestrates multi-container Docker applications.

If you need assistance installing docker: https://docs.docker.com/desktop/

Docker-compose is included in Docker Desktop, but if you need assistance installing docker compose: https://docs.docker.com/compose/install/

You can check if you have Docker installed by running the following command:

docker -v
docker compose -v

Once you have Docker and Docker Compose installed, you can proceed to the next step.

Cloning the Repository

The first step is cloning the AutoGPT repository to your computer. To do this, open a terminal window in a folder on your computer and run:

git clone https://github.com/Significant-Gravitas/AutoGPT.git
If you get stuck, follow this guide.

Once that's complete you can close this terminal window.

Running the backend services

To run the backend services, follow these steps:

  • Within the repository, clone the submodules and navigate to the autogpt_platform directory:

     git submodule update --init --recursive
     cd autogpt_platform
    
    This command will initialize and update the submodules in the repository. The supabase folder will be cloned to the root directory.

  • Copy the .env.example file available in the supabase/docker directory to .env in autogpt_platform:

     cp supabase/docker/.env.example .env
    
    This command will copy the .env.example file to .env in the supabase/docker directory. You can modify the .env file to add your own environment variables.

  • Run the backend services:

     docker compose up -d
    
    This command will start all the necessary backend services defined in the docker-compose.combined.yml file in detached mode.

Running the frontend application

To run the frontend application, follow these steps:

  • Navigate to frontend folder within the autogpt_platform directory:

     cd frontend
    

  • Copy the .env.example file available in the frontend directory to .env in the same directory:

     cp .env.example .env
    
    You can modify the .env within this folder to add your own environment variables for the frontend application.

  • Run the following command:

     npm install
     npm run dev
    
    This command will install the necessary dependencies and start the frontend application in development mode.

Checking if the application is running

You can check if the server is running by visiting http://localhost:3000 in your browser.

Notes:

By default the application for different services run on the following ports:

Frontend UI Server: 3000 Backend Websocket Server: 8001 Execution API Rest Server: 8006