# agents-cli > CLI commands and coding-agent skills to create, evaluate, deploy and observe agents on Google Cloud. Supports ADK (Python and Go), LangChain, the Claude Agent SDK and your own templates. Every page has a Markdown version at index.md, listed below. All page URLs: https://google.github.io/agents-cli/sitemap.xml - [Set up Agents CLI and build a first agent](https://google.github.io/agents-cli/setup.md): step-by-step instructions for a coding agent ## Guide - [Getting started](https://google.github.io/agents-cli/guide/getting-started/index.md): Paste one line into your coding agent. It installs Agents CLI, designs a first agent with you, and runs it locally. - [The lifecycle](https://google.github.io/agents-cli/guide/lifecycle/index.md): Agents CLI is opinionated about the loop that takes an agent from "looks good in a notebook" to "live in production." This page maps that loop. - [Tutorial: Build your first agent](https://google.github.io/agents-cli/guide/quickstart-tutorial/index.md): For beginners who want to build, evaluate, and deploy an agent using a coding agent. - [Tutorial: Manual workflow](https://google.github.io/agents-cli/guide/hands-on-tutorial/index.md): For developers who prefer to type every command themselves, without a coding agent. - [Use cases](https://google.github.io/agents-cli/guide/use-cases/index.md): Agents CLI scaffolds, evaluates, and deploys agents from the descriptions you provide to your coding agent. Use it to build: - [Authentication](https://google.github.io/agents-cli/guide/authentication/index.md): Agents CLI sits on top of several tools, and each one authenticates separately. This page covers the three layers (your coding agent, your agent's model calls, and deployment), what each one - [Development guide](https://google.github.io/agents-cli/guide/development/index.md): This guide covers the full development workflow, from defining what you're building to monitoring it in production. It follows the same phases your coding agent uses through the - [Project structure](https://google.github.io/agents-cli/guide/project-structure/index.md): For developers who want to understand the layout of a generated agent project. - [Control cost](https://google.github.io/agents-cli/guide/cost/index.md): Four things drive what an agent costs: model tokens, compute for the deployed service, judge calls during evaluation, and telemetry storage. Measure first, then change one setting at a time and check - [Extensions](https://google.github.io/agents-cli/guide/extensions/index.md): An extension changes what an agents-cli command does, or adds a new command, without forking the tool. Use one to run a different agent framework, add your org's checks to any command, or give your - [Using extensions](https://google.github.io/agents-cli/guide/extensions/using/index.md): Extensions adapt agents-cli to a workflow it doesn't ship with, such as a different agent framework, an org's deploy policy, or a command of your own, without forking the tool. - [Authoring extensions](https://google.github.io/agents-cli/guide/extensions/authoring/index.md): The quickest path is ad-hoc: drop a single agents-cli-extension.yaml at your project root (next to agents-cli-manifest.yaml). It's auto-loaded at project scope, so you don't need extension add. Commit - [First-party frameworks](https://google.github.io/agents-cli/guide/extensions/first-party/index.md): A framework ships as a template you scaffold from, not as an extension you install. The template carries its own agents-cli-extension.yaml, so the project gets the framework's command overrides with - [Evaluation guide](https://google.github.io/agents-cli/guide/evaluation/index.md): Run structured evaluations to confirm your agent calls the right tools, produces quality responses, and handles edge cases. Grading uses the GenAI Eval SDK in Gemini platform. Evaluation works with - [Debug a failing agent](https://google.github.io/agents-cli/guide/debugging/index.md): To debug a failing agent, reproduce the failure with one prompt, save it as an eval case, grade it to see which metric fails and why, read the trace to find the step that went wrong, then rerun and - [Deployment](https://google.github.io/agents-cli/guide/deployment/index.md): Deploy your agent to a development environment or production with a CI/CD pipeline. - [CI/CD and production](https://google.github.io/agents-cli/guide/cicd/index.md): Set up a CI/CD pipeline that tests on pull request, deploys to staging on merge, and then promotes the same commit to production behind an approval gate. - [Observability](https://google.github.io/agents-cli/guide/observability/index.md): Every project that Agents CLI scaffolds ships with OpenTelemetry instrumentation that automatically exports traces to Cloud Trace. The instrumentation gives you: - [Cloud Trace](https://google.github.io/agents-cli/guide/observability/cloud-trace/index.md): For developers who have deployed an agent and want to verify tracing works and inspect telemetry data. - [BigQuery Agent Analytics plugin](https://google.github.io/agents-cli/guide/observability/bq-agent-analytics/index.md): For teams who want SQL-based analytics on agent behavior, token usage, and conversation patterns. ## Reference - [CLI reference](https://google.github.io/agents-cli/cli/index.md): Complete reference for every command in Agents CLI in Gemini platform (the agents-cli binary). - [Skills reference](https://google.github.io/agents-cli/reference/skills/index.md): Skills are context files that agents-cli setup installs into coding agents (Antigravity CLI, Claude Code, Codex, Cursor and others). They provide domain-specific guidance for working with generated - [Security and trust](https://google.github.io/agents-cli/guide/security/index.md): Agents CLI runs commands on your machine and in your Google Cloud project, and a coding agent often runs them for you. This page lists what runs, what it changes, and how to limit it. - [About this project](https://google.github.io/agents-cli/reference/about/index.md): - Issues and suggestions: open an issue on GitHub - Share your experience: reach out at agents-cli@google.com - [Migrate eval datasets](https://google.github.io/agents-cli/reference/eval-dataset-migration/index.md): If you started using Agents CLI before the eval commands were rebuilt around the GenAI Eval SDK in Gemini platform, you may have evaluation files under tests/eval/evalsets/ using the older ADK EvalSet