Agents CLI

What is Agents CLI?

Agents CLI, installed as agents-cli, is a Google command-line tool and a set of skills that make an existing coding agent better at building and deploying AI agents on Google Cloud. It is not a coding assistant itself. Claude Code, Codex, Antigravity CLI or another agent calls its commands to create a project from the ADK template, run the agent, grade it against an evaluation dataset, deploy it and register it with Gemini. Seven skills teach the agent the development lifecycle, ADK Python code patterns, scaffolding, evaluation methods, deployment targets such as Agent Runtime, Cloud Run and GKE, publishing and observability. The CLI also works on its own from the terminal. Setup needs Python 3.11 or newer, uv and Node.js, and local development can use an AI Studio API key, though deployment needs Google Cloud. The tool is free and open source; costs come from the Google Cloud resources you deploy.

Use cases

• Scaffold a new ADK agent project
• Let Claude Code deploy agents to Google Cloud
• Evaluate agents against datasets and metrics
• Auto-tune agent prompts with eval data
• Set up CI/CD for an agent project
• Register an agent with Gemini
• Add observability with Cloud Trace

Who it's for

• AI engineers
• Python developers
• Platform teams
• Google Cloud users

Why use Agents CLI

• Your coding agent gets ready-made knowledge of ADK patterns, evals and deployment instead of improvising Google Cloud commands.
• One CLI covers creating, evaluating, deploying and publishing an agent, so you learn fewer separate tools.
• Local work such as create, run and eval needs only an AI Studio API key, not a Google Cloud project.
• Existing agent projects can add deployment and CI/CD with scaffold enhance.
• It is free to install, and telemetry can be turned off with an environment variable.

Agents CLI features

• Seven agent skills for lifecycle, ADK code, scaffold, eval, deploy, publish and observability
• agents-cli create for new agent projects from the adk template
• agents-cli scaffold enhance to add deployment or CI/CD to existing projects
• Evaluation commands for run, grade, compare, analyze and optimize
• Synthesized multi-turn eval scenarios for local agents
• agents-cli deploy to Google Cloud
• agents-cli publish gemini to register an agent
• Infrastructure setup for single-project and CI/CD pipelines
• Works standalone or with Antigravity CLI, Claude Code and Codex

Agents CLI integrations

• Claude Code
• Codex
• Antigravity CLI
• Google Cloud
• Cloud Run
• GKE
• Cloud Trace
• AI Studio
• Gemini

How to get started with Agents CLI

1. Install with uvx google-agents-cli setup, or add only the skills with npx skills add google/agents-cli.
2. Open your coding agent, such as Antigravity CLI, Claude Code or Codex.
3. Ask it to build an agent; it uses agents-cli create and the ADK skills to scaffold the project.
4. Run agents-cli eval run to grade the agent's traces against your dataset and metrics.
5. Deploy with agents-cli deploy, set up infrastructure or CI/CD, and publish with agents-cli publish gemini.

Agents CLI limitations

• Requires Python 3.11+, uv and Node.js
• Deployment and cloud features need a Google Cloud project
• It is a tool for coding agents rather than a coding agent itself
• Collects usage telemetry by default; opt out with AGENTS_CLI_TELEMETRY=0

Agents CLI pricing

Agents CLI is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

Agents CLI alternatives

The main Agents CLI alternatives listed on Debuly are LangGraph, OpenAI Agents SDK, CrewAI, Strands Agents, LangChain and OpenLIT. The table compares pricing and platforms; order is A–Z.

1. 

   CrewAI

   Multi-agent framework and platform for building AI agent crews in Python or a visual editor, then deploying and monitoring them.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit CrewAI (official site)
2. 

   LangChain

   Open-source framework for building LLM agents, paired with LangSmith for tracing, evals and agent deployment.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit LangChain (official site)
3. 

   LangGraph

   Low-level open-source orchestration framework and runtime for building stateful, long-running AI agents as graphs.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit LangGraph (official site)
4. 

   OpenAI Agents SDK

   Open-source Python framework for building multi-agent workflows with tools, handoffs, guardrails, tracing, sandboxes and voice agents.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit OpenAI Agents SDK (official site)
5. 

   OpenLIT

   Open-source, OpenTelemetry-native platform for tracing, evaluating and guarding AI agents, with cost and GPU monitoring

   Developer platformsCodingAutomation and agents
   Open sourceVisit OpenLIT (official site)
6. 

   Strands Agents

   Free Apache-2.0 SDK for creating and running Python and TypeScript AI agents, with built-in tools, MCP, memory and multi-agent patterns.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit Strands Agents (official site)

Agents CLI FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from avatars.githubusercontent.com · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.