ADK Agent Examples

Full explainer video is available on YouTube - Analyzer Agent + ADK Intro, Job Finder Agent(MistralOCR + Qwen3). Read detailed blog 1 and blog 2

This repository contains various agent demos built with Google's ADK (Agent Development Kit), showcasing different patterns and capabilities for building AI agents. ADK is a flexible and modular framework that makes agent development feel more like software development. While optimized for Gemini and the Google ecosystem, it's model-agnostic, deployment-agnostic, and compatible with other frameworks. ADK enables developers to create, deploy, and orchestrate agentic architectures ranging from simple tasks to complex workflows, with features like multi-agent pipelines, tool integration, and sequential processing.

If you're looking to build some Production grade agents with Google ADK or other frameworks, read this awesome guide by Nebius AI - Agent 101: Launching production-grade agents at scale

LLM Integration

All demos in this repository are using open-source LLMs:

• Meta-Llama-3.1-8B-Instruct - Used in most agent implementations
• Llama-3_1-Nemotron-Ultra-253B - Used for advanced analysis in the Analyzer Agent
• Qwen3-14B - Used for Job Finder Agent

These models are integrated via LiteLLM, which ADK supports for connecting to various model providers.

Agent Demos

Agent	Pattern	Description	Details
Analyzer Agent	5-agent sequential pipeline	AI trends analysis with multiple data sources	README
Email Agent	Single agent with tool	Email integration with Resend API	README
Sequential Agent	3-agent sequential pipeline	News aggregator combining IPL and AI news	README
Multi-Tool Search	Root agent with delegation	Modular search with agent delegation	README
Job Finder	4-agent sequential pipeline	Resume analysis and job matching	README

For detailed information about each agent, please refer to the individual READMEs in their respective directories.

Implementation Patterns Demonstrated

This repository demonstrates several important ADK patterns:

1. Sequential Agent Chaining - Multiple agents executing in sequence, with outputs becoming inputs for the next agent.
2. Tool Integration - Using external APIs and services as tools within agents.
3. Agent Delegation - A root agent delegating tasks to specialized sub-agents.
4. Multi-Model Approach - Using different LLM models for different tasks based on capabilities.
5. Specialized Agents - Agents designed for specific tasks like search, summary, analysis, etc.

Setup

1. Clone the repository:

git clone https://github.com/Astrodevil/ADK-Agent-Examples.git
cd ADK-Agent-Examples

2. Install ADK:

pip install google-adk

3. Create and activate a virtual environment:

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

4. Install dependencies:

pip install -r requirements.txt

5. Set up your environment variables for the agent you want to run:

# Example for analyzer agent
cp analyzer_agent/.env.example analyzer_agent/.env

Then edit the .env file to include your API keys.

Usage

Running Agents with ADK CLI

# Dev UI - Visual interface for testing and debugging agents
adk web

# Terminal - Run agents directly in the terminal
adk run analyzer_agent
adk run email_adk_agent
adk run seq_adk_agent
adk run multi_tool_search_agent
adk run jobfinder_agent

# API Server - Create a local FastAPI server for API testing
adk api_server

API Keys Required

You'll need to set up accounts and obtain API keys for:

Service	Purpose	Required For
Nebius AI	LLM inference	All agents
Exa	Web search	Most agents
Tavily	Specialized search	Some agents
Firecrawl	Web scraping	Analyzer agent
Resend	Email sending	Email agent
Mistral AI	OCR processing	Job Finder agent
Linkup	Job search	Job Finder agent

See each agent's README for specific requirements.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.