The same research agent built three times — Google ADK on Cloud Run, Strands on Bedrock AgentCore, Agent Framework on Container Apps — all speaking A2A v1.0. Where the platforms differ, where the models differ, and what has to be held constant before either is readable.
This article provides a step by step comparison of the same research agent built three times, on Google ADK, AWS Strands and Microsoft Agent Framework, all three speaking A2A to one coordinator.
The code is here:
github.com/xbill9/multicloud-a2a-subagent
What is this project trying to Do?
This project aims to find out what actually differs between the three hyperscalers' agent frameworks once the protocol between them already works.
A Google ADK agent on Cloud Run, serving A2A to clients that are not ADK — a Strands agent on Bedrock AgentCore and an Agent…
A step by step guide to running a Strands agent on Amazon Bedrock AgentCore Runtime, serving the A2A protocol to callers on…
What is this project trying to do? Three AI agents, each built with a different vendor's...
All three hyperscalers now ship an agent framework, and all three speak A2A. The protocol page will...
Every directed edge between Bedrock AgentCore, Microsoft Foundry, and Google ADK, deployed and measured over A2A v1.0 — the…
A Strands agent on Bedrock AgentCore Runtime serving A2A to callers on Google Cloud and Azure. The AgentCore container contract,…
