Technology

An embodied AI stack, built end to end.

We design the model, the silicon, the actuators, and the software that ties them together. Vertical integration is how we close the loop between perception, reasoning, and action.

Embodied Foundation Model

A vision-language-action transformer trained on millions of hours of human and teleoperated demonstration. It generalizes across tasks without per-task fine-tuning.

Tactile Sensing

Sub-millimeter capacitive arrays on each fingertip feed a closed-loop control system that adjusts grip in real time, so L-1 can hold an egg or torque a jar lid.

Whole-body Planning

A unified planner reasons about base, torso, and arm motion together — eliminating the awkward stop-and-go behavior of stitched-together robotic systems.

On-device Inference

Our model runs on a fanless compute module inside L-1. Nothing about your home leaves the device unless you opt in.