Entry #1: Fully Offline
Omocube can run fully offline, without depending on anyone else's server. Every LLM agent and ML/DL model runs locally on Omocube's onboard processor.
The point was to give the AI a body to experience things firsthand while having all experiences tied to Omocube itself. By running everything onboard, Omocube’s experiences remain its own rather than being distributed across multiple places. This creates the foundation for a stronger, continuous, and persistent self that belongs only to this physical machine.
Whatever Omocube sees and hears stays with it, with no telemetry pipeline and no third-party service standing between Omocube and the people around it. No API keys, cloud account, or server holding data that was never asked to be uploaded.
Online extras, like web search, remain optional and uses a search engine that doesn't collect or store user data.