Getting Started with Autonomys Agents Framework via CLI

1. Install dependencies:

   yarn install
   • Windows users will need to install Visual Studio C++ Redistributable. It can be found here: https://aka.ms/vs/17/release/vc_redist.x64.exe

2. Create a character configuration:

   yarn create-character your_character_name

   This will create a new character with the necessary configuration files based on the example template.

3. Configure your character:

   • Edit characters/your_character_name/config/.env with your API keys and credentials
   • Customize characters/your_character_name/config/config.yaml for agent behavior
   • Define personality in characters/your_character_name/config/your_character_name.yaml

4. Generate SSL certificates (required for API server):

   yarn generate-certs

5. Run the agent:

      cd <to/agent/project>
      yarn start <your_character_name>

   If you have stored workspace files (characters, certs, and .cookies directories) in a custom location, use the --workspace argument with the absolute path to your desired directory:

   # Specify a workspace path
   yarn start your_character_name --workspace=/path/to/workspace
    
   # Run in headless mode (no API server)
   yarn start your_character_name --headless

Running Multiple Characters

You can run multiple characters simultaneously, each with their own configuration and personality:

1. Create multiple character configurations:

   yarn create-character alice
   yarn create-character bob

2. Configure each character separately with different personalities and API settings.

3. Run each character in a separate terminal session:

   # Terminal 1
   yarn start alice
    
   # Terminal 2
   yarn start bob

4. Each character will:

   • Have its own isolated memory and experience
   • Run its own API server on the specified port
   • Execute tasks according to its unique schedule and personality

Docker Deployment

You can also run your agents using Docker. This provides isolation and makes it easy to run multiple agents simultaneously.

Prerequisites

• Docker installed on your system (Installation Guide)
• Docker Compose Plugin required (Compose Plugin Installation)
• Character configuration set up (follow steps from the Getting Started section)

Running with Docker

1. Generate your character’s docker-compose file

First make the script executable:

chmod +x ./generate-compose.sh

Then generate the compose file:

./generate-compose.sh <your-character-name> [HOST_PORT] [API_PORT]

Examples:

# Run Alice on port 3011 with API port on 3011
./generate-compose.sh Alice 3011 3011
 
# Run Bob on port 3012 with API port on 3011
./generate-compose.sh Bob 3012 3011

2. Manage the Docker container

Build and start the container:

docker compose -f docker-compose-{character-name}.yml up -d

Stop and remove the container:

docker compose -f docker-compose-{character-name}.yml down

View container logs:

docker compose -f docker-compose-{character-name}.yml logs -f

Access container shell:

docker exec -it autonomys-agent-{character-name} bash