#agents

Google shipped ADK for Android in May. I built a Compose app — clean architecture, MVI, Hilt, persistent chat history — where a Gemini agent calls real on-device functions, and hit every sharp edge the docs don't mention.

A deep technical look at the multi-agent workflow that scraped the entire awesome-selfhosted dataset — nine runs, every architectural failure, exact agent counts and token numbers per run, and how it ended with Python bypassing agents entirely.

I had two old Intel NUCs, an obsession with AI agents that actually do things, and a decision to make about which machine gets which job. This is how I split them — and why the answer wasn't obvious.