⚠️ EARLY PREVIEW — BREAKING CHANGES FROM 1.x

This is an early alpha 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:

pip install google-adk==2.0.0a1

pip install google-adk will NOT install this version.

• 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.

pip install google-adk==2.0.0a1

Requirements: Python 3.11+.

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.",
)

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)],
)

# Interactive CLI
adk run path/to/my_agent

# Web UI
adk web path/to/agents_dir

• Getting Started: https://google.github.io/adk-docs/
• Samples: See contributing/workflow_samples/ and contributing/task_samples/ for workflow and task API examples.

See CONTRIBUTING.md for details.

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