Skip to content

lavinigam-gcp/build-with-adk

Repository files navigation

Build with ADK

Learn to build production-ready AI agents with Google's Agent Development Kit

A collection of real-world multi-agent examples built with Google Agent Development Kit (ADK). Each agent demonstrates different ADK patterns and capabilities - from video generation to code execution.


Featured Agents

Ad Campaign Agent

Multi-agent platform for retail video advertising.

  • AI Video Generation - Gemini + Veo 3.1 for professional ad content
  • Human-in-the-Loop - Review and approval workflow
  • Analytics Dashboard - In-store metrics with AI-generated charts
cd ad-campaign-agent && make install && make dev

Retail AI Location Strategy

Multi-agent pipeline for retail site selection.

  • Market Research - Live data with Google Search integration
  • Competitor Mapping - Geographic analysis with Google Maps API
  • Executive Reports - Professional outputs with infographics and audio summaries
cd retail-ai-location-strategy && make install && make dev

Equity Research Agent

Multi-agent pipeline for professional equity research reports.

  • Human-in-the-Loop Planning - User approval for research plans
  • Batch Chart Generation - Agent Engine Sandbox for secure code execution
  • Multi-Market Support - US, India, Europe, Asia with locale-specific metrics
cd adk-equity-deep-research && make setup && make dev

Why This Repository?

Building AI agents that work in production requires more than prompt engineering. These examples demonstrate:

  • Multi-agent orchestration - Hierarchical and sequential pipelines
  • Tool integration - Google Maps, Search, GCS, and custom APIs
  • Structured outputs - Pydantic schemas for type-safe responses
  • Production deployment - Cloud Run and Vertex AI Agent Engine

Getting Started

Prerequisites

Quick Start

git clone https://github.com/lavinigam-gcp/build-with-adk.git
cd build-with-adk

# Choose an agent
cd ad-campaign-agent          # Video advertising
cd retail-ai-location-strategy # Site selection
cd adk-equity-deep-research   # Equity research

# Setup and run
cp .env.example app/.env  # Edit with your API keys
make install && make dev

# Open http://localhost:8501

Resources


Author

Lavi Nigam GitHub LinkedIn X

Collaborators


License

Apache 2.0 - See individual agent folders for specific licenses.