| Google Adds Open-Source Development Kit To Vertex AI |
| Written by Kay Ewbank | |||
| Tuesday, 15 April 2025 | |||
|
Google has added an Agent Development Kit (ADK) to Vertex AI, along with an agent engine and an Agent2Agent protocol that provides agents with a common, open language for collaboration. The announcement was made at Google's annual Google Cloud Next conference, saying it will make it possible to build an AI agent in under 100 lines of Python code. Vertex AI is a fully-managed, unified AI development platform for building and using generative AI. It uses Google AI Studio, Agent Builder, and includes 130 foundation models including Gemini 1.5 Pro, all from Vertex AI.
The new ADK framework for designing agents is built on the same framework that is used by Google Agentspace and Google Customer Engagement Suite (CES) agents, and there's a good selection of examples and extensible sample agents in Agent Garden, the framework's sample collection. The framework is currently limited to Python, with more languages coming later in the year. Google says the framework will make it possible to build an AI agent in under 100 lines of Python code. It can be used to specify how agents reason and collaborate using deterministic guardrails and orchestration controls. Developers can interact with their agents using conversations with bidirectional audio and video streaming. Google says ADK works with your model of choice – whether it is Gemini or your any model accessible via Model Garden. Beyond Google's models, you can choose across 200+ models from providers like Anthropic, Meta, Mistral AI, AI21 Labs, CAMB.AI, and Qodo. Deployment targets include containerized production deployments such as Cloud Run, Kubernetes, or Vertex AI. ADK also supports Model Context Protocol (MCP) for secure connections between data and agents. Alongside the ADK, Google has released Agent Engine, a fully managed runtime in Vertex AI that can be used to deploy custom agents to production with built-in testing, release, and reliability. Agent Engine handles agent context, infrastructure management, scaling complexities, security, evaluation, and monitoring. It can be used to deploy agents built using any framework, including ADK, LangGraph, Crew.ai, or others. It also supports session context, so agents can recall your past conversations and preferences. There's also a new Agent2Agent protocol that provides agents with a common, open language to collaborate – no matter which framework or vendor they are built on. Google says it is driving this open initiative, partnering with 50+ industry leaders. Google Agent Development Kit is available now.
More InformationRelated ArticlesGoogle Releases Vertex AI Agent Builder Google Releases Gemma Open Models Google Rebrands Bard With Subscription Google Adds Code Generation To Bard To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin. 
Comments
or email your comment to: comments@i-programmer.info |
