Back to Adk Python

Agent Development Kit (ADK) 2.0 Beta

README.md

2.0.0b13.0 KB
Original Source

Agent Development Kit (ADK) 2.0 Beta

<h2 align="center"> </h2> <h3 align="center"> An open-source, code-first Python framework for building, evaluating, and deploying sophisticated AI agents with flexibility and control. </h3> <h3 align="center"> Important Links: <a href="https://google.github.io/adk-docs/">Docs</a>, <a href="https://github.com/google/adk-samples">Samples</a> & <a href="https://github.com/google/adk-web">ADK Web</a>. </h3>

⚠️ BETA RELEASE — BREAKING CHANGES FROM 1.x

This is an early beta of ADK 2.0. It includes breaking changes to the agent API, event model, and session schema. Do NOT use with ADK 1.x databases or sessions — they are incompatible. APIs are subject to change without notice.

Install only with an explicit version pin:

bash
pip install google-adk==2.0.0b1

pip install google-adk will NOT install this version.


🔥 What's New in 2.0

  • Workflow Runtime: A graph-based execution engine for composing deterministic execution flows for agentic apps, with support for routing, fan-out/fan-in, loops, retry, state management, dynamic nodes, human-in-the-loop, and nested workflows.

  • Task API: Structured agent-to-agent delegation with multi-turn task mode, single-turn controlled output, mixed delegation patterns, human-in-the-loop, and task agents as workflow nodes.

🚀 Installation

bash
pip install google-adk==2.0.0b1

Requirements: Python 3.11+.

Quick Start

Agent

python
from google.adk import Agent

root_agent = Agent(
    name="greeting_agent",
    model="gemini-2.5-flash",
    instruction="You are a helpful assistant. Greet the user warmly.",
)

Workflow

python
from google.adk import Agent, Workflow

generate_fruit_agent = Agent(
    name="generate_fruit_agent",
    instruction="Return the name of a random fruit. Return only the name.",
)

generate_benefit_agent = Agent(
    name="generate_benefit_agent",
    instruction="Tell me a health benefit about the specified fruit.",
)

root_agent = Workflow(
    name="root_agent",
    edges=[("START", generate_fruit_agent, generate_benefit_agent)],
)

Run Locally

bash
# Interactive CLI
adk run path/to/my_agent

# Web UI
adk web path/to/agents_dir

📚 Documentation

🤝 Contributing

See CONTRIBUTING.md for details.

📄 License

This project is licensed under the Apache 2.0 License — see the LICENSE file for details.