Find your next open-source project

Search by name, purpose, or keyword — or paste a GitHub repository URL
All skills

agent-platform-deploy

Deploy a Model Garden model to an Agent Platform endpoint, then check status or undeploy it.

  • Part of google/skills
  • 10.3k installs
  • Machine Learning · Model serving

When to use it

You have a model picked out and a project ready, but still need it running on an endpoint with the right machine type and cost estimate.

For example

You say

Use agent-platform-deploy to deploy a Gemma model from Model Garden to a new endpoint in us-central1 on g2-standard-24, and show me the hourly cost first.

You get
  • Deploy command with cost estimate
  • Endpoint display name
  • Operation name for status checks

How it works

  • Presents a confirmation card with the exact command, hardware, and hourly cost before deploying.
  • Checks the live catalog instead of naming model versions from memory.
  • Suggests an alternative region when quota or capacity blocks the deploy.

Before installing

Needs an authenticated gcloud CLI with the project and region set; some Hugging Face models also need a Hugging Face access token.

This skill includes 2 scripts your assistant may run on your computer.