Overview
To use Vertex AI Agent Engine, you must first develop an agent that can be deployed on Vertex AI Agent Engine. The easiest way to develop an agent is to use one of the framework-specific templates that we provide. Framework-specific templates automatically handle some of the common aspects of developing an agent such as serializing objects and separating the code that initializes an agent from the code that responds to prompts. We provide the following framework-specific templates:
| Framework | Description |
|---|---|
| Agent Development Kit (preview) | Designed based on Google's internal best practices for developers building AI applications or teams needing to rapidly prototype and deploy robust agent-based solutions. |
| LangChain | Easier to implement for basic use cases because of its predefined configurations and abstractions. |
| LangGraph | Graph-based approach to defining workflows, with advanced human-in-the-loop and rewind/replay capabilities. |
| AG2 (formerly AutoGen) | AG2 provides multi-agent conversation framework as a high-level abstraction for building LLM workflows. |
| LlamaIndex (preview) | LlamaIndex's query pipeline offers a high-level interface for creating Retrieval-Augmented Generation (RAG) workflows. |
If your use case doesn't align with one of the framework-specific templates, you can develop your own custom agent.
Agent2Agent (A2A) protocol
If you are building a multi-agent system, we highly recommend reviewing the A2A Protocol. A2A Protocol is an open standard that enables seamless communication and collaboration between AI agents, regardless of their underlying frameworks. It was donated by Google Cloud to the Linux Foundation in June 2025. To use the A2A SDKs, or try out the samples, check out the GitHub repository.