⚠️ BREAKING CHANGES FROM 1.x

This release includes breaking changes to the agent API, event model, and session schema. Sessions generated by ADK 2.0 are readable by ADK 1.28+ (extra fields will be ignored), but are incompatible with older 1.x versions.

• 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

Requirements: Python 3.10+.

To install optional integrations, you can use the following command:

pip install "google-adk[extensions]"

The release cadence is roughly bi-weekly.

Beginner Note: ADK applications are built using two main classes: Agent (defines an AI's instructions, tools, and behavior) and Workflow (orchestrates agents and tasks in a graph-based flow).

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 (supports multi-agent directories or pointing directly to a single agent folder)
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.