Google ADK: Agent Development Kit

​Google Cloud recently introduced the Agent Development Kit (ADK) at NEXT 2025, a new open-source framework purpose-built to help you design, deploy, and evaluate intelligent multi-agent systems with ease. Whether you’re looking to orchestrate agents, integrate tools, or deploy production-grade agentic applications, ADK provides everything you need in one developer-friendly toolkit.

​According to the official blog, the Agent Development Kit is:

​a powerful, open-source framework designed to simplify the development of production-ready AI agents and multi-agent systems with flexible tooling, rich integrations, and deployment options built for scale.

​In this session, we’ll go beyond the basics and explore what it really takes to build and deploy collaborative agents using ADK.

​We’ll answer questions like:

• ​What does it mean to build multi-agent systems with ADK?

• ​How do agents delegate tasks, stream audio/video, and interact with tools like LangChain or Vertex AI models?

• ​How do you deploy, evaluate, and integrate these agents into real-world products?

​🚀 According to the launch at Google Cloud NEXT, with ADK you can:

• ​🧠 Build modular multi-agent systems with clear delegation and orchestration

• ​🔧 Integrate with any model via Vertex AI or LiteLLM

• ​🛠️ Use tools, libraries, or even other agents inside your agents

• ​🎥 Enable bidirectional streaming for rich, natural multimodal interaction

• ​🧪 Evaluate performance before deployment using built-in test frameworks

• ​📦 Deploy anywhere, including Google Cloud's Vertex AI Agent Engine

​Key Features of ADK

• ​Multi-Agent by Design: Compose agents into scalable, collaborative systems with hierarchical delegation.

• ​Rich Tool & Model Ecosystem: Integrate models from Gemini, Anthropic, Meta, Mistral AI, and more. Equip agents with tools from LangChain, LlamaIndex, or define your own.

• ​Streaming Interaction: Build natural experiences with voice and video support.

• ​Flexible Orchestration: Choose between deterministic workflows or adaptive routing using LLM logic.

• ​Integrated Dev Experience: Inspect and debug with a CLI and visual UI.

• ​Evaluation + Deployment: Built-in test framework + easy containerized deployment to any environment, including Vertex AI.

​Join us live to learn what you can build, ship, and share with Google’s ADK!

​📚 You’ll learn:

• ​How to build multi-agent applications using ADK’s Pythonic, open-source framework

• ​How to delegate tasks and coordinate agents using ADK’s orchestration tools

• ​How to evaluate and deploy agents to Vertex AI’s managed infrastructure

​🤓 Who should attend the event:

• ​AI Engineers who want to build production agentic applications with the latest tools

• ​AI Engineering leaders who want to understand the latest agent orchestration frameworks

​Speakers:

• ​Dr. Greg” Loughnane is the Co-Founder & CEO of AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. Since 2021, he has built and led industry-leading Machine Learning education programs.  Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher.  He loves trail running and is based in Dayton, Ohio.

• ​Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator YouTube who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.

​Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.