What we build
Two AI primitives. One proof discipline.
A governed control plane and a governed inference engine.
The products
Built from proof. Deployed as primitives.
These are not generic AI tools repackaged with a governance label. Each one is built from the same mathematical proof discipline that governs every SMARTHAUS engagement.
Mathematically Governed Control Plane
Universal Control Plane (UCP)
A desktop app that governs every AI connection on your device. AI agents, MCP servers, models, tools, rules, and policies — all connected through one governed control plane. Runs locally. Enforces locally. For individuals on one device or enterprises across a fleet.
Learn more →Intent-Based Inference Primitive
Sermo Arbiter Inferentiae Determinata (SAID)
A GPU-first deterministic inference engine that selects and executes LLM inference with mathematical guarantees. Ranks models using multi-objective optimization, routes requests deterministically, and produces signed decision receipts for every inference. Standalone desktop app or embeddable runtime.
Learn more →In development
The primitives underneath.
These engines are real and running in research. The packaged products aren't ready yet.
Storage substrate
Memory that holds proofs alongside meaning, so retrieval returns evidence and not just an embedding lookup.
Intent engine
Turns ambiguous requests into measurable intent fields the rest of the stack can route, gate, and prove against.
Orchestration engine
Routes intent into governed action across services, with runtime invariants that fail loudly the moment a guarantee stops holding.
Meaning extraction
Decomposes language into structured meaning so the system operates on semantics and roles, not just token sequences.