The layer between a brain and a body.
nex-ON turns “understand the goal” into perceive, choose a tool, and act. Because perception, tooling and control are interfaces rather than fixed implementations, a new robot or a new skill is a registration, not a rebuild.
Three layers, one contract between them.
Our own frontier model reasons about the goal and orchestrates the body, deciding mid-conversation which capability to call next.
Vision, measurement, motion, tooling and sensor feeds are swappable tools registered against an interface, not hard wiring.
Next comes Orio, our wheeled companion robot for the home. The same orchestration is architected for humanoids, AMRs and mixed fleets.
The capabilities the brain can call.
Dangerous by exception, never by default.
The safety model is a property of the platform, not of any one task: it transfers to any actuated hardware we put underneath it.
What it is built from.
A clean conversation, with the diagnostics behind it.
The operator sees only the exchange. Everything else (tool arguments, depth readings, IK results, arming state) lands in timestamped logs for the engineer.