#!/usr/bin/env python3 """ Google ADK — Official AI Agent Development Kit

Google's open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents. 18.7K+ GitHub stars.

Quick start: pip install google-adk adk create my_agent adk run my_agent

GitHub: https://github.com/google/adk-python License: Apache 2.0 """

=== Quick Use ===

pip install google-adk

Then create your first agent:

from google.adk.agents import Agent from google.adk.tools import google_search

Define a research agent

research_agent = Agent( name="researcher", model="gemini-2.0-flash", description="Research assistant that finds and summarizes information", instruction="""You are a helpful research assistant. Use Google Search to find accurate, up-to-date information. Always cite your sources.""", tools=[google_search], )

=== Multi-Agent Example ===

from google.adk.agents import Agent, SequentialAgent

writer = Agent( name="writer", model="gemini-2.0-flash", instruction="Write clear, concise content based on research findings.", )

Chain agents: researcher -> writer

pipeline = SequentialAgent( name="research_pipeline", sub_agents=[research_agent, writer], )

=== Evaluation ===

ADK includes built-in evaluation tools:

adk eval my_agent --test-file tests.json

=== Deployment ===

Deploy to Google Cloud with one command:

adk deploy cloud_run my_agent --project=my-gcp-project

=== Key Features ===

- Multi-agent orchestration (Sequential, Parallel, Loop)

- 100+ built-in tools (Search, Code Exec, Vertex AI)

- Session & memory management

- Built-in evaluation framework

- One-command deployment to Cloud Run / Vertex AI

- MCP server compatibility

- Streaming responses

- Custom tool creation

print("Google ADK installed. Run: adk create my_agent")