google / agents-cli

agents-cli The CLI and skills for building agents on Gemini Enterprise Agent Platform. agents-cli 是用于在 Gemini 企业级智能体平台（Gemini Enterprise Agent Platform）上构建智能体的命令行工具（CLI）及技能集。

Turn your favorite coding assistant into an expert at building and deploying agents on Google Cloud. Agents CLI in Agent Platform (agents-cli) gives your coding agent the skills and commands to build, scale, govern, and optimize enterprise-grade agents — so you don’t have to learn every CLI and service yourself. 将你最喜爱的编程助手转变为在 Google Cloud 上构建和部署智能体的专家。Agent Platform 中的 Agents CLI (agents-cli) 为你的编程智能体提供了构建、扩展、管理和优化企业级智能体所需的技能与命令，让你无需亲自学习每一个 CLI 工具和服务。

Works seamlessly with: Antigravity CLI • Claude Code • Codex • and any other coding agent. 可与以下工具无缝协作：Antigravity CLI、Claude Code、Codex 以及任何其他编程智能体。

Get Started

快速开始

Prerequisites: Python 3.11+, uv, and Node.js. 先决条件：Python 3.11+、uv 和 Node.js。

Install
安装 uvx google-agents-cli setup Or just the skills — your coding agent will handle the rest 或者仅安装技能——你的编程智能体将处理其余工作 npx skills add google/agents-cli
Open your coding agent
打开你的编程智能体 Launch Antigravity CLI, Claude Code, Codex, or any coding agent you prefer. 启动 Antigravity CLI、Claude Code、Codex 或你偏好的任何编程智能体。
Build your first agent
构建你的第一个智能体 Ask your coding agent to build something — e.g. “Use agents-cli to build a caveman-style agent that compresses verbose text into terse, technical grunts” 让你的编程智能体构建一些东西——例如：“使用 agents-cli 构建一个原始人风格的智能体，将冗长的文本压缩为简短的技术性短语。”

See the full tutorial for a step-by-step walkthrough. Browse the full documentation → 查看完整教程以获取分步指南。浏览完整文档 →

Agent Skills

智能体技能

Skill	What your coding agent learns
技能	你的编程智能体将学会什么
google-agents-cli-workflow	Development lifecycle, code preservation rules, model selection
google-agents-cli-workflow	开发生命周期、代码保留规则、模型选择
google-agents-cli-adk-code	ADK Python API — agents, tools, orchestration, callbacks, state
google-agents-cli-adk-code	ADK Python API — 智能体、工具、编排、回调、状态
google-agents-cli-scaffold	Project scaffolding — create, enhance, upgrade
google-agents-cli-scaffold	项目脚手架 — 创建、增强、升级
google-agents-cli-eval	Evaluation methodology — metrics, datasets, LLM-as-judge, adaptive rubrics
google-agents-cli-eval	评估方法论 — 指标、数据集、LLM 作为评判者、自适应评分标准
google-agents-cli-deploy	Deployment — Agent Runtime, Cloud Run, GKE, CI/CD, secrets
google-agents-cli-deploy	部署 — Agent Runtime, Cloud Run, GKE, CI/CD, 密钥管理
google-agents-cli-publish	Gemini Enterprise registration
google-agents-cli-publish	Gemini Enterprise 注册
google-agents-cli-observability	Observability — Cloud Trace, logging, third-party integrations
google-agents-cli-observability	可观测性 — Cloud Trace, 日志记录, 第三方集成

CLI Commands

CLI 命令

Command	What it does
命令	功能描述
agents-cli setup	Install CLI + skills to coding agents
agents-cli setup	为编程智能体安装 CLI 和技能
agents-cli scaffold <name>	Create a new agent project
agents-cli scaffold <name>	创建一个新的智能体项目
agents-cli eval generate	Run agent on eval dataset, produce traces
agents-cli eval generate	在评估数据集上运行智能体，生成追踪记录
agents-cli eval grade	Run agent evaluations on the traces
agents-cli eval grade	对追踪记录进行智能体评估
agents-cli deploy	Deploy to Google Cloud
agents-cli deploy	部署到 Google Cloud
agents-cli publish gemini-enterprise	Register with Gemini Enterprise
agents-cli publish gemini-enterprise	在 Gemini Enterprise 中注册

FAQ

常见问题解答

Is this an alternative to Antigravity CLI, Claude Code, or Codex? 这是 Antigravity CLI、Claude Code 或 Codex 的替代品吗？ No. agents-cli is a tool for coding agents, not a coding agent itself. It provides the CLI commands and skills that make your coding agent better at building, evaluating, and deploying ADK agents on Google Cloud. 不是。agents-cli 是为编程智能体提供的工具，它本身不是编程智能体。它提供 CLI 命令和技能，使你的编程智能体能更好地在 Google Cloud 上构建、评估和部署 ADK 智能体。

How is this different from just using adk directly? 这与直接使用 ADK 有什么不同？ ADK is an agent framework. agents-cli gives your coding agent the skills and tools to build, evaluate, and deploy ADK agents end-to-end. ADK 是一个智能体框架。agents-cli 为你的编程智能体提供了端到端构建、评估和部署 ADK 智能体的技能与工具。

Do I need Google Cloud? 我需要 Google Cloud 吗？ For local development (create, run, eval), no — you can use an AI Studio API key to run Gemini with ADK locally. For deployment and cloud features, yes. 对于本地开发（创建、运行、评估），不需要——你可以使用 AI Studio API 密钥在本地运行带有 ADK 的 Gemini。但对于部署和云端功能，则需要。

Can I use this with an existing agent project? 我可以将其用于现有的智能体项目吗？ Yes. agents-cli scaffold enhance adds deployment and CI/CD to existing projects. 可以。agents-cli scaffold enhance 可以为现有项目添加部署和 CI/CD 功能。

Can I use agents-cli without a coding agent? 我可以在没有编程智能体的情况下使用 agents-cli 吗？ Yes. The CLI works standalone — you can run agents-cli scaffold, eval, deploy, and every other command directly from your terminal. The skills just make it easier for coding agents to do it for you. 可以。该 CLI 可以独立运行——你可以直接在终端中运行 agents-cli scaffold、eval、deploy 以及其他所有命令。技能集只是让编程智能体能更轻松地为你完成这些工作。

Feedback

反馈

We value your input — it helps us improve agents-cli for the community. 我们重视你的反馈——这有助于我们为社区改进 agents-cli。

Bugs & feature requests: open an issue — 👍 the ones you want prioritized. Bug 和功能请求：请提交 Issue，并为你希望优先处理的内容点赞（👍）。

Share what you built: we’d love to hear about your projects! Reach out at agents-cli@google.com to share your agent or provide feedback. 分享你的成果：我们很乐意了解你的项目！请通过 agents-cli@google.com 联系我们，分享你的智能体或提供反馈。

Contributing

贡献

The best way to contribute is through feedback: bug reports, feature requests, and ideas shared via issues to directly shape our roadmap. See the contributing guide for details. 贡献的最佳方式是通过反馈：通过 Issue 分享 Bug 报告、功能请求和想法，直接影响我们的路线图。详情请参阅贡献指南。

Terms of Service

服务条款

agents-cli leverages Google Cloud APIs. When you deploy agents, you’ll be deploying resources in your own Google Cloud project and will be responsible for those resources. Please review the Google Cloud Service Terms for details. agents-cli 利用了 Google Cloud API。当你部署智能体时，你将在自己的 Google Cloud 项目中部署资源，并需对这些资源负责。请查阅 Google Cloud 服务条款以了解详情。

Preview

预览

This feature is subject to the “Pre-GA Offerings Terms” in the Google Cloud Terms of Service. 此功能受 Google Cloud 服务条款中的“预发布（Pre-GA）产品条款”约束。