AutoGPT + Docker guide¶

Important

Docker Compose version 1.29.0 or later is required to use version 3.9 of the Compose file format. You can check the version of Docker Compose installed on your system by running the following command:

docker compose version

This will display the version of Docker Compose that is currently installed on your system.

If you need to upgrade Docker Compose to a newer version, you can follow the installation instructions in the Docker documentation: https://docs.docker.com/compose/install/

Basic Setup¶

Make sure you have Docker installed, see requirements
Create a project directory for AutoGPT
```
mkdir AutoGPT
cd AutoGPT
```

In the project directory, create a file called docker-compose.yml:

docker-compose.yml> for <= v0.4.7

version: "3.9"
services:
  auto-gpt:
    image: significantgravitas/auto-gpt
    env_file:
      - .env
    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 want to make use of these files
      ## you must have them existing in the same folder as this docker-compose.yml
      #- type: bind
      #  source: ./azure.yaml
      #  target: /app/azure.yaml

docker-compose.yml> for > v0.4.7 (including master)

version: "3.9"
services:
  auto-gpt:
    image: significantgravitas/auto-gpt
    env_file:
      - .env
    ports:
      - "8000:8000"  # remove this if you just want to run a single agent in TTY mode
    profiles: ["exclude-from-up"]
    volumes:
      - ./data:/app/data
      ## allow auto-gpt to write logs to disk
      - ./logs:/app/logs
      ## uncomment following lines if you want to make use of these files
      ## you must have them existing in the same folder as this docker-compose.yml
      ## component configuration file
      #- type: bind
      #  source: ./config.json
      #  target: /app/config.json

Download .env.template and save it as .env in the AutoGPT folder.
Follow the standard configuration instructions, from step 3 onwards and excluding poetry install steps.
Pull the latest image from Docker Hub
```
docker pull significantgravitas/auto-gpt
```
4. Optional: mount configuration file. If you have component configuration file, for example config.json, place it in classic/original_autogpt/data/ directory. Or place it in classic/original_autogpt/ and uncomment the line in docker-compose.yml that mounts it. To learn more about configuring, see Component configuration

Docker only supports headless browsing

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

Developer Setup¶

Tip

Use this setup if you have cloned the repository and have made (or want to make) changes to the codebase.

Copy .env.template to .env.
Follow the standard configuration instructions, from step 3 onwards and excluding poetry install steps.

Running AutoGPT with Docker¶

After following setup instructions above, you can run AutoGPT with the following command:

docker compose run --rm auto-gpt

This creates and starts an AutoGPT container, and removes it after the application stops. This does not mean your data will be lost: data generated by the application is stored in the data folder.

Subcommands and arguments work the same as described in the user guide:

Run AutoGPT:
```
docker compose run --rm auto-gpt serve
```

Run AutoGPT in TTY mode, with continuous mode.

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

Run AutoGPT in TTY mode and install dependencies for all active plugins:
```
docker compose run --rm auto-gpt run --install-plugin-deps
```

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

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