HomeProjectsArticlesPK BoardAbout
Explore Projects

Agent Starter Pack

Normal
GitHub Python Apache-2.0

Description

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

Key Features

  • Production-ready templates for GenAI agents on Google Cloud
  • Multiple agent types — ADK, LangGraph, RAG, multi-agent, Live API
  • One-command CI/CD setup with Cloud Build and GitHub Actions
  • Built-in Vertex AI evaluation and interactive playground
  • Terraform-based infrastructure with monitoring and observability
  • Firebase Studio and Cloud Shell zero-setup support

Use Cases

💡 Scaffolding a new AI agent project with Google Cloud best practices
💡 Deploying RAG agents with Vertex AI Search or Vector Search
💡 Setting up production CI/CD pipelines for agent testing and deployment
💡 Building multimodal agents with Gemini Live API integration

Strengths & Limitations

✅ Strengths

  • • High community interest (6.5k stars)
  • • Permissive open-source license (Apache-2.0)
  • • Responsive to issues, low backlog

Tags

python agent framework tools devops

Categories

💻 Coding Agent

Quick Start

Run `uvx agent-starter-pack create` (or `pip install agent-starter-pack && agent-starter-pack create`). Select a template, and the scaffolded project includes backend, frontend, and deployment infra ready to explore.
Visit GitHub Visit Website View Docs

Related Projects

AI Agents for Beginners

73.8k · Jupyter Notebook
Active A+

12 Lessons to Get Started Building AI Agents by Microsoft. Hands-on curriculum covering core agent concepts, tool use, and multi-agent collaboration.

agentframeworkpython +1
  • · 12 structured lessons - Covers AI agent fundamentals, tool use, and multi-agent collaboration in a progressive curriculum
  • · Microsoft Agent Framework - Hands-on code samples built on Azure AI Foundry Agent Service V2
  • · Multi-language support - Auto-translated via GitHub Action with 50+ language versions available
View full details → View on GitHub

Scientific Agent Skills

42.1k · Python
Active A+

A set of ready-to-use Agent Skills for research, science, engineering, analysis, finance and writing across multiple coding agents.

agentcodingtools +2
  • · 142 ready-to-use scientific skills — Covers 17+ fields: bioinformatics, cheminformatics, proteomics, clinical research, medical imaging, and more
  • · 100+ scientific database integration — Unified access to 78+ public databases including PubChem, ChEMBL, UniProt, COSMIC, ClinicalTrials.gov
  • · 70+ optimized Python package skills — Dedicated skills for RDKit, Scanpy, PyTorch Lightning, scikit-learn with curated documentation and examples
View full details → View on GitHub

Cased Kit

1.3k · Python
Stale B

The toolkit for AI devtools context engineering. Build with codebase mapping, symbol extraction, and many kinds of code search to help AI agents better understand and operate on codebases.

codingagenttools +1
  • · Codebase mapping and symbol extraction for functions, classes, and constructs
  • · Multiple code search modes: regex (ripgrep), AST pattern matching, and symbol usage tracking
  • · LLM context preparation with intelligent file chunking for context windows
View on GitHub