agentregistry
Agents
Deploy
Local

Local

Deploy an agent from agentregistry to your local environment.

Local deployments spin up Docker containers on your local machine from images that exist on your machine or that can be pulled from the image location reference that agentregistry points to.

Before you begin

  1. Follow the Get started guide to set up agentregistry and start the agentregistry daemon.
  2. Publish an agent.

Deploy the agent

  1. Save your Gemini API key as an environment variable. To retrieve your API key, log in to the Google AI Studio and select API Keys. The key is used to interact with the agent via the Gemini LLM provider.

    export GOOGLE_API_KEY=<apikey>

  2. Deploy the agent to your local environment. The following command spins up a Docker container by using Docker compose.

    arctl agent deploy myagent --runtime local

  3. List the containers in your environment. Verify that you see a container with the ghcr.io/myagent:latest image.

    docker ps

    Example output:

    CONTAINER ID   IMAGE                    COMMAND                  CREATED              STATUS                  PORTS                                                                                                                                                                                                                                                                                                                                                                                                                                 NAMES
816ad44cba11   ghcr.io/myagent:latest   "kagent-adk run --ho…"   About a minute ago   Up About a minute       0.0.0.0:40529->40529/tcp, [::]:40529->40529/tcp

  1. Open the agentregistry UI.

  2. Go into the Published view.

  3. Select the agent image that you published and click Deploy.

  4. From the Deployment destination drop down, select Local (Docker Compose) and click Deploy.

  5. Switch to the Deployed and verify that you see the deployed agent.

  6. List the containers in your environment. Verify that you see a container with the ghcr.io/myagent:latest image.

    docker ps

    Example output:

    CONTAINER ID   IMAGE                    COMMAND                  CREATED              STATUS                  PORTS                                                                                                                                                                                                                                                                                                                                                                                                                                 NAMES
816ad44cba11   ghcr.io/myagent:latest   "kagent-adk run --ho…"   About a minute ago   Up About a minute       0.0.0.0:40529->40529/tcp, [::]:40529->40529/tcp

Cleanup

  1. Open the agentregistry UI and navigate to the Deployed view.
  2. Find the agent deployment that you want to remove. Then, click Remove.
Kubernetes