This repository provides a convenient and secure solution to run Auto-GPT in a Docker container with a web-based terminal. Running Auto-GPT in a Docker container isolates it from the host system, preventing accidental damage from commands like rm -rf or apt install <whatever>. Additionally, it ensures a consistent and easy-to-maintain environment.

• Runs Auto-GPT in a Docker container for improved security and maintainability
• Provides a browser-based terminal UI using gotty
• Accessible via http://127.0.0.1:8080, or by IP address

1. Clone the repository and navigate to the project directory

2. Copy the sample AI settings file and edit to suit your needs.

   cp ai_settings.sample ai_settings.yaml
   

3. Copy the sample .env file and edit to suit your needs, you can read about these settings on the auto-gpt repo.

   cp .env.template .env
   

4. Run the Docker container:

   docker-compose up -d
   

To access the terminal UI via a browser, visit http://127.0.0.1:8080 or the IP address of the system it's running on.

• Check if gotty can pass audio from the autogpt --speak option
• Verify that integration with ElevenLabs is functional (should be okay, but untested)