google/agents-cli

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 12 seconds ago
Added to GitGenius on September 11th, 2026
Created on April 8th, 2026
Open Issues & Pull Requests: 33 (+0)
GitHub issues: Enabled
Number of forks: 660
Total Stargazers: 5,917 (+0)
Total Subscribers: 41 (+0)

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Issue API getrepoissuespagesummary failed: 429 Rate limit exceeded. Please try again later.

Detailed Description

Agents CLI is a command-line tool that equips coding assistants with skills and commands for building, deploying, and managing AI agents on Google Cloud's Gemini Enterprise Agent Platform.

The tool solves the problem of coding assistants lacking domain knowledge about agent development and Google Cloud deployment. Rather than requiring developers to manually teach their coding assistant about multiple CLIs and services, Agents CLI packages this knowledge into discrete skills that the assistant can invoke. The approach works by providing both a CLI interface and a set of skills covering the full agent lifecycle: workflow and development practices, the Agent Development Kit Python API, project scaffolding, evaluation methodology, deployment to various Google Cloud targets, agent registration, and observability integration.

Developers should adopt this tool if they use a coding assistant like Antigravity CLI, Claude Code, or similar tools and want to build agents on Google Cloud without manually orchestrating multiple services. It suits teams building enterprise-grade agents who want their coding assistant to handle scaffolding, evaluation, and deployment automation. The tool is designed to work seamlessly with any coding agent, not just Google's offerings.

The project maintains a substantial base of adopters who report issues from real-world use rather than the core team driving the issue tracker. Maintainers respond to new issues and pull requests within a few days. Work in the issue tracker centers on known issues, enhancements, and documentation improvements.