A code-first Python framework for building, evaluating, and deploying AI agents. It uses a graph-based execution engine for orchestrating structured delegation and deterministic execution flows.
Project overview
A code-first Python framework for building, evaluating, and deploying AI agents. It uses a graph-based execution engine for orchestrating structured delegation and deterministic execution flows.
Project type
AI Agent · Workflow · Infrastructure
Use cases
Coding & Development · Automation
Deployment
Refer to project documentation
License
Apache-2.0
Best for
Developers and AI engineers who write Python code and need a graph-based execution engine for orchestrating agents with deterministic execution flows.
Key capabilities
A graph-based execution engine for composing deterministic execution flows for agentic apps, supporting routing, fan-out/fan-in, loops, retry, state management, dynamic nodes, human-in-the-loop, and nested workflows.
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.
Class for defining an AI's instructions, tools, and behavior.
Run agents locally using a CLI interface.
Run and test multi-agent directories or single agent folders using a local Web UI.
Limitations and risks
ADK 2.0 introduces breaking changes to the agent API, event model, and session schema. It is incompatible with older 1.x versions.
The framework requires external AI model inference utilizing generative AI models.
Getting started
Install the framework easily via standard pip command (`pip install google-adk`). Developers can then run agents locally using the provided CLI interface or the local Web UI.
Evidence and sources
GitHub project description: An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
README: An open-source, code-first Python framework for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
README: 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 manage…
README: 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…
README: > **Beginner Note:** ADK applications are built using two main classes: > **`Agent`** (defines an AI's instructions, tools, and behavior) and > **`Workflow`** (orchestrates agents…