# GoogleCloudPlatform/agent-starter-pack

Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.

Repository: https://github.com/GoogleCloudPlatform/agent-starter-pack
Canonical: https://ross.abutalabs.com/products/agent-starter-pack
Homepage: http://goo.gle/agents-cli
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agents, gcp, gemini, genai-agents, generative-ai, llmops, mlops, observability
Last push: 2026-07-21T23:42:40+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 93, release rhythm 69, longevity 41
- inputs: {"age_days": 579, "days_push": 43, "days_rel": 130, "gap_med": 2.0, "n_releases_24m": 83}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6545, forks 1502 (observed 2026-08-28T04:09:45.081888+00:00)

## What it is
A Python package from Google Cloud Platform that provides production-ready templates for building and deploying GenAI agents on Google Cloud, with built-in CI/CD, evaluation, and observability. It is now in maintenance mode, with active development moved to the successor project agents-cli.

## Use cases
- scaffold a production-ready AI agent on Google Cloud
- deploy a RAG or ReAct agent to GCP with CI/CD
- set up Vertex AI evaluation for my LLM agent
- add observability and monitoring to a GenAI agent
- bootstrap a multi-agent application with Terraform and deployment pipelines
- ship a Gemini-powered chatbot to production quickly

## When to choose
- you are maintaining an existing project already built with Agent Starter Pack
- you need critical fixes only and want the stable, documented GCP agent templates
- you want a battle-tested scaffold with Terraform, CI/CD, and Vertex AI evaluation out of the box

## When to avoid
- you are starting a new project - use the successor agents-cli instead
- you need new templates, features, or deployment targets, since none will be added
- you deploy outside Google Cloud, as the templates are GCP-centric

## Facets
- artifact type: framework
- maturity: maintenance
- function: agent-framework, llm-inference, rag, ci-cd, monitoring, deployment, infrastructure-as-code, cli
- domain: large-language-models, artificial-intelligence, cloud-computing
- platform: python, cloud, cli
- tags: gemini, vertex-ai, llmops, genai-agents, google-cloud, templates, observability, scaffolding, superseded-by-agents-cli, ai-agents, devops, retrieval-augmented-generation, docker

## Member repositories
- GoogleCloudPlatform/agent-starter-pack (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:45.081888+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:44:05.995574+00:00, confidence not recorded.
  - readme: https://github.com/GoogleCloudPlatform/agent-starter-pack (fetched 2026-08-28T04:09:45.081888+00:00, sha 74438b647bac)
  - homepage: http://goo.gle/agents-cli (fetched 2026-08-29T08:40:29.956783+00:00, sha 2d8193baf138)
- Data as of 2026-08-30T08:39:29.467469+00:00.