TAU-0.12B
Experimental edge model
An early compact research model exploring continual adaptation and highly constrained on-device inference.
Internal research
Researching what
comes next.
Alongside the TAU app, Vecorps explores efficient models, memory and adaptation through internal research. These are areas of study, not released product capabilities.
01
Research projects and models
TAU-2.4B
Personal AI research model
An experimental model exploring hybrid sequence modelling, persistent personal context and local adaptation.
Internal research
TAU-3B
Future runtime research
A higher-capacity research model exploring possible future on-device runtimes.
Internal research
CRT
Persistent intelligence research
An experimental research project exploring persistent internal state, learning from experience, and self-directed activity over time.
Early-stage research
02Open questions
On-device efficiency
How capable personal AI can run within the memory, power and latency constraints of personal devices.
Adaptation
How personal AI could become more useful over time without requiring a central cloud profile.
Memory
How systems can preserve useful continuity while keeping memory visible and under user control.
Personal intelligence
How models, memory and tools might work together in future personal AI systems.