google/agents-cli provides a CLI and a suite of skills that teach coding assistants how to scaffold, evaluate, and deploy AI agents on Google Cloud. It acts as an orchestration layer for existing coding agents rather than functioning as a standalone coding agent itself.
Project overview
It addresses the need to learn multiple disparate Google Cloud CLIs and services by consolidating the agent lifecycle into a set of coding agent skills and commands.
Project type
AI Coding
Use cases
Coding & Development
Deployment
Refer to project documentation
License
Apache-2.0
Best for
Developers building, evaluating, and deploying AI agents on Google Cloud who want to use their existing coding assistants for lifecycle management.
Key capabilities
Provides commands for scaffolding, running, evaluating, deploying, and publishing agents.
A suite of skills that teach coding agents the development lifecycle, ADK API patterns, and observability.
Generates execution traces over datasets, grades performance with metrics, and analyzes failure modes.
Limitations and risks
The project is subject to Pre-GA Offerings Terms and might have limited support.
Users are responsible for the costs of the Google Cloud resources deployed by the tool. A paid service is required for deployment and cloud features.
Getting started
Setup is rated as easy. Users can run `uvx google-agents-cli setup` or `npx skills add google/agents-cli`, then open their coding agent or use the CLI directly to scaffold an agent.
Alternatives and comparisons
A fair-code platform to build and deploy AI agents and workflows with a visual canvas, custom code, and numerous integrations, offering an alternative approach to agent automation.
Provides a visual authoring experience for AI agents and workflows with built-in API and MCP servers, allowing flows to be turned into tools integrated into any framework.
Provides a collection of hand-built, tested, open-source AI agents and RAG apps for users looking for examples to learn from and build upon.