Agent Development Kit (ADK)

Agent Development Kit (ADK) is a flexible and modular framework for developing and deploying AI agents. While optimized for Gemini and the Google ecosystem, ADK is model-agnostic, deployment-agnostic, and is built for compatibility with other frameworks.

ADK is designed to make agent development feel more like software development, making it easier for developers to create, deploy, and orchestrate agentic architectures ranging from simple tasks to complex workflows.

Set up Environment & Install ADK

Create and activate a virtual environment (recommended):

bash

# Create virtual environment
python -m venv .venv

# Activate (each new terminal)
# macOS/Linux
source .venv/bin/activate

# Windows CMD
.venv\Scripts\activate.bat

# Windows PowerShell
.venv\Scripts\Activate.ps1

Install ADK

Install ADK by running the following command:

bash

pip install google-adk

Create an Agent Project

Run the following command to create a new agent project:

bash

adk create my_agent

Project Structure

The created agent project has the following structure:

Folder Structure

📁 my_agent/
├── 📄 agent.py        # main agent code
├── 📄 .env            # API keys or project IDs
└── 📄 __init__.py

Update Your Agent Project

The agent.py file contains a root_agent definition, which is the only required element of an ADK agent. You can also define tools for the agent to use.

Below is an example of adding a get_current_time tool:

Python

from google.adk.agents.llm_agent import Agent

# Mock tool implementation
def get_current_time(city: str) -> dict:
    """Returns the current time in a specified city."""
    return {"status": "success", "city": city, "time": "10:30 AM"}

root_agent = Agent(
    model='gemini-3-flash-preview',
    name='root_agent',
    description="Tells the current time in a specified city.",
    instruction="You are a helpful assistant that tells the current time in cities. Use the 'get_current_time' tool for this purpose.",
    tools=[get_current_time],
)

Set Your API Key

This project uses the Gemini API, which requires an API key. You can create an API key from Google AI Studio.

Store your API key in the .env file:

bash

echo 'GOOGLE_API_KEY="YOUR_API_KEY"' > .env

Replace YOUR_API_KEY with your actual API key.

Run Your Agent

You can run your ADK agent using either the command-line interface or the web interface:

1. Run with command-line interface:
   • Use the following command:

bash

adk run my_agent

2. Run with web interface:
   • Start the web interface using the following command:

bash

adk web --port 8000

Note: Run this command from the parent directory that contains your my_agent/ folder.

This command starts a web server with a chat interface. You can access it at:

• http://localhost:8000
• http://127.0.0.1:8000

Select your agent from the top-left corner and start interacting with it.