Setting up Auto-GPT

📋 Requirements

Choose an environment to run Auto-GPT in (pick one):

Docker (opens in a new tab) (recommended)
Python 3.10 or later (instructions: for Windows (opens in a new tab))
VSCode + devcontainer (opens in a new tab)

🗝️ Getting an API key

Get your OpenAI API key from: https://platform.openai.com/account/api-keys (opens in a new tab).

Attention

To use the OpenAI API with Auto-GPT, we strongly recommend setting up billing (AKA paid account). Free accounts are limited (opens in a new tab) to 3 API calls per minute, which can cause the application to crash.

You can set up a paid account at Manage account > Billing > Overview (opens in a new tab).

Important

It's highly recommended that you keep keep track of your API costs on the Usage page (opens in a new tab). You can also set limits on how much you spend on the Usage limits page (opens in a new tab).

For OpenAI API key to work, set up paid account at OpenAI API > Billing

Setting up Auto-GPT

Set up with Docker

Make sure you have Docker installed, see requirements
Pull the latest image from Docker Hub (opens in a new tab)
```
docker pull significantgravitas/auto-gpt
```
Create a folder for Auto-GPT

In the folder, create a file called docker-compose.yml with the following contents:

version: "3.9"
services:
  auto-gpt:
    image: significantgravitas/auto-gpt
    depends_on:
      - redis
    env_file:
      - .env
    environment:
      MEMORY_BACKEND: ${MEMORY_BACKEND:-redis}
      REDIS_HOST: ${REDIS_HOST:-redis}
    profiles: ["exclude-from-up"]
    volumes:
      - ./auto_gpt_workspace:/app/auto_gpt_workspace
      - ./data:/app/data
      ## allow auto-gpt to write logs to disk
      - ./logs:/app/logs
      ## uncomment following lines if you have / want to make use of these files
      #- ./azure.yaml:/app/azure.yaml
      #- ./ai_settings.yaml:/app/ai_settings.yaml
  redis:
    image: "redis/redis-stack-server:latest"

Create the necessary configuration files. If needed, you can find templates in the repository (opens in a new tab).
Continue to Run with Docker

Note "Docker only supports headless browsing"

Auto-GPT uses a browser in headless mode by default: HEADLESS_BROWSER=True. Please do not change this setting in combination with Docker, or Auto-GPT will crash.

Set up with Git

Important

Make sure you have Git (opens in a new tab) installed for your OS.

Info "Executing commands"

To execute the given commands, open a CMD, Bash, or Powershell window.
On Windows: press ++win+x++ and pick Terminal, or ++win+r++ and enter cmd

Clone the repository

git clone -b stable https://github.com/Significant-Gravitas/Auto-GPT.git

Navigate to the directory where you downloaded the repository
```
cd Auto-GPT
```

Set up without Git/Docker

Warning

We recommend to use Git or Docker, to make updating easier.

Download Source code (zip) from the latest stable release (opens in a new tab)
Extract the zip-file into a folder

Configuration

Find the file named .env.template in the main Auto-GPT folder. This file may be hidden by default in some operating systems due to the dot prefix. To reveal hidden files, follow the instructions for your specific operating system: Windows (opens in a new tab), macOS (opens in a new tab).
Create a copy of .env.template and call it .env; if you're already in a command prompt/terminal window: cp .env.template .env.
Open the .env file in a text editor.
Find the line that says OPENAI_API_KEY=.
After the =, enter your unique OpenAI API Key without any quotes or spaces.
Enter any other API keys or tokens for services you would like to use.

Note

To activate and adjust a setting, remove the # prefix.
Save and close the .env file.

Info "Using a GPT Azure-instance"

If you want to use GPT on an Azure instance, set USE_AZURE to True and make an Azure configuration file:

Rename azure.yaml.template to azure.yaml and provide the relevant azure_api_base, azure_api_version and all the deployment IDs for the relevant models in the azure_model_map section:
- fast_llm_model_deployment_id: your gpt-3.5-turbo or gpt-4 deployment ID
- smart_llm_model_deployment_id: your gpt-4 deployment ID
- embedding_model_deployment_id: your text-embedding-ada-002 v2 deployment ID

Example:

# Please specify all of these values as double-quoted strings
# Replace string in angled brackets (<>) to your own ID
azure_model_map:
    fast_llm_model_deployment_id: "<my-fast-llm-deployment-id>"
        ...

Details can be found in the openai-python docs (opens in a new tab), and in the Azure OpenAI docs (opens in a new tab) for the embedding model. If you're on Windows you may need to install an MSVC library (opens in a new tab).

Running Auto-GPT

Run with Docker

Easiest is to use docker-compose. Run the commands below in your Auto-GPT folder.

Build the image. If you have pulled the image from Docker Hub, skip this step.
```
docker-compose build auto-gpt
```
Run Auto-GPT
```
docker-compose run --rm auto-gpt
```
By default, this will also start and attach a Redis memory backend. If you do not want this, comment or remove the depends: - redis and redis: sections from docker-compose.yml.

You can pass extra arguments, e.g. running with --gpt3only and --continuous:

docker-compose run --rm auto-gpt --gpt3only --continuous

If you dare, you can also build and run it with "vanilla" docker commands:

docker build -t auto-gpt .
docker run -it --env-file=.env -v $PWD:/app auto-gpt
docker run -it --env-file=.env -v $PWD:/app --rm auto-gpt --gpt3only --continuous

Run with Dev Container

Install the Remote - Containers (opens in a new tab) extension in VS Code.
Open command palette with ++f1++ and type Dev Containers: Open Folder in Container.
Run ./run.sh.

Run without Docker

Simply run the startup script in your terminal. This will install any necessary Python packages and launch Auto-GPT.

On Linux/MacOS:
```
./run.sh
```
On Windows:
```
.\run.bat
```

If this gives errors, make sure you have a compatible Python version installed. See also the requirements.

Home Usage