Four Iceberg Tools, Three Agent Frameworks: What Ports, and What Doesn't

This project involves building a small Apache Iceberg data agent using three different frameworks: Google ADK, AWS Strands, and Microsoft Agent Framework. Each version is tested against five Iceberg catalogs to measure performance differences through direct verification. As hyperscalers release their own agent frameworks and Apache Iceberg becomes a standard open table format for universal data readability, the project investigates whether an agent designed to read this portable data is itself portable across platforms.