agent-starter-pack

GoogleCloudPlatform/agent-starter-pack

A repository for production-ready templates to deploy AI Agents on Google Cloud.

6.5k
Stars
1.5k
Forks
46
Open issues
64
Watchers
Python Apache-2.0Last pushed Jun 30, 2026

Overview

Contains Python-based templates aimed at easing the deployment process of generative agents in a production environment, featuring built-in CI/CD, evaluation, and observability tools.

Categories

Tags

Similar tools

Install

pip install agent-starter-pack

README

🚀 Agent Starter Pack

Try in Firebase Studio

⚠️ Agent Starter Pack is in maintenance mode — switch to agents-cli

Active development has moved to agents-cli, the next evolution of Agent Starter Pack. ASP will continue to receive critical fixes only — no new features, no new templates, no new deployment targets. New projects should start with agents-cli; existing projects should migrate.

uvx google-agents-cli setup

Migration takes minutes — your agent code, tests, Terraform, and CI/CD carry over with no rewrites.

What you gain:

  • 🛠️ Unified CLI in place of the Makefile — run, deploy, eval run, eval compare, playground, lint, and more
  • 🧠 Bundled coding-agent skills that turn Claude Code, Gemini CLI, or Codex into an ADK expert
  • 🔁 End-to-end lifecycle tooling: scaffold → eval → deploy → publish → observe
  • ☁️ First-class support for Google Cloud's Agent Platform

Migration guide  •  Get started  •  Docs  •  GitHub  •  PyPI


A Python package that provides production-ready templates for GenAI agents on Google Cloud.

Focus on your agent logic—the starter pack provides everything else: infrastructure, CI/CD, observability, and security.

⚡️ Launch🧪 Experiment✅ Deploy🛠️ Customize
Pre-built agent templates (ReAct, RAG, multi-agent, Live API).Vertex AI evaluation and an interactive playground.Production-ready infra with monitoring, observability, and CI/CD on Cloud Run or Agent Engine.Extend and customize templates according to your needs. 🆕 Now integrating with Gemini CLI

⚡ Get Started in 1 Minute

From zero to production-ready agent in 60 seconds using uv:

uvx agent-starter-pack create
✨ Alternative: Using pip

If you don't have uv installed, you can use pip:

# Create and activate a Python virtual environment
python -m venv .venv && source .venv/bin/activate

# Install the agent starter pack
pip install --upgrade agent-starter-pack

# Create a new agent project
agent-starter-pack create

That's it! You now have a fully functional agent project—complete with backend, frontend, and deployment infrastructure—ready for you to explore and customize.

🔧 Enhance Existing Agents

Already have an agent? Add production-ready deployment and infrastructure by running this command in your project's root folder:

uvx agent-starter-pack enhance

See [Installation Guide](https://googlecloudplatform