Google's Agent Development Kit (ADK) for Python is an open-source toolkit aimed at streamlining the creation, evaluation, and deployment of AI agents. The latest release, v2.1.0, introduces several key features and improvements. A core component of ADK 2.0 is its Workflow Runtime, a graph-based execution engine that facilitates the composition of deterministic execution flows for agentic applications. This engine supports advanced functionalities such as routing, fan-out/fan-in, loops, retry mechanisms, state management, dynamic nodes, and human-in-the-loop interactions, including nested workflows. Additionally, the toolkit features a Task API for structured agent-to-agent delegation, offering multi-turn task modes, single-turn controlled output, mixed delegation patterns, and the ability to integrate task agents as workflow nodes. The project is licensed under Apache 2.0 and requires Python 3.11+ for installation.
Google's ADK-Python: An Open-Source Toolkit for AI Agent Development
Google has released ADK-Python, an open-source, code-first Python toolkit designed for building, evaluating, and deploying AI agents. The toolkit, currently at version 2.1.0, emphasizes flexibility and control in agent development and includes a graph-based execution engine for workflows and a structured Task API for agent-to-agent delegation.
Why it matters
ADK-Python provides developers with a robust, open-source framework for creating sophisticated AI agents. Its focus on a code-first approach, combined with features like a workflow runtime and a Task API, offers significant control and flexibility, potentially accelerating the development and deployment of advanced agentic applications.