I wanted to create a responsive pet robot that provides light entertainment and interaction without increasing screen time. It is primarily for anyone seeking fun, interactive desk gadget. It reduces network usage because all inference happens locally; only occasional the model updates or telemetry need network transfer. Because it is on-device processing there is no cloud latency or dependency. It is cheaper to scale and operate long-term. It is private: All audio processing happens on the device, keeping user data local.
