Initialize Agent

The init command sets up a new agent deployment by creating an agent and a deployment in VideoSDK cloud. It also generates a videosdk.yaml configuration file in your project directory.

Initialize

Create a new agent and deployment.

Usage

videosdk agent init --name my-agent

Options

Option	Short	Description	Default
--name	-n	Name for your deployment	Auto-generated if not provided
--template	-t	Template ID to use (e.g., Template01)	None

What Happens

1. Cloud Creation: The CLI communicates with VideoSDK cloud to create a new agent and a corresponding deployment.
2. Config Generation: A videosdk.yaml file is created in your current directory. This file contains the unique IDs for your agent and deployment.
3. Project Setup: Your local project is now linked to the cloud resources.

Example Output

$ videosdk agent init --name my-agent

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  Initializing Deployment
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

⠋ Initializing Deployment...

✓ Deployment initialized successfully

ℹ Next step: Build your agent Docker image
  videosdk agent build --image <your-docker-username>/<image-name>:<tag>

videosdk.yaml Structure

The generated videosdk.yaml file will look like this:

agent:
  id: ag_48bnvu
  name: agent-test
deploy:
  id: ddv_h3b5sd

Field	Description
agent.id	Unique identifier for your AI agent
agent.name	Name of your agent
deploy.id	Unique identifier for this specific deployment

Notes

• You should run this command in the root of your agent's project directory.
• The videosdk.yaml file should be committed to your version control system (e.g., Git).
• If you already have a videosdk.yaml file, running init again will prompt you or might overwrite settings depending on the version.

Next Steps

After initializing your agent, the next step is to build and push your agent's Docker image. See the Build & Push documentation for more details.