A small humanoid robot you can talk to: walks with a reinforcement-learned policy, waves and dances, shows a face with lip sync and speaks - its brain is a local LLM you run yourself (Ollama or any OpenAI-compatible API). MuJoCo simulation, sim-to-real.
Universal ONNX policy deployment for robots. Any trained control policy, any hardware, bound by name not index. Ships a zero-config preflight doctor that catches wiring bugs before the robot moves.
JAX-native robotics: URDF/MJCF import, differentiable MJX dynamics, system identification, calibrated actuators & sensors, whole-body control, and per-unit attested digital twins — one calibrated model from sim to silicon.
Declarative robotics: describe a robot, world, and tests in YAML; compile to a headless ROS 2 + Gazebo sim and get machine-readable pass/fail evidence. Built for coding agents (CLI + MCP).
