Skip to main content

Bolt Runtime

Bolt any policy onto any robot. Bolt Runtime (boltrt) is a native C++ deployment runtime for learned robot policies.

  • Modular observations: adapt a new policy by composing registered observation terms in its YAML.
  • Seamless sim-to-real: MuJoCo and real robots implement one interface, decoupled from the policy, so switching is just --backend.
  • Fast: native C++ runs the full policy step 3.25× faster than the Python stack.

A run is always the combination of three configurations plus an optional task:

boltrt [--task tracking] --robot g1 --policy policy.yaml --backend mujoco
PieceOwns
robotjoint/body names, MJCF model, dynamics and torque limits
policyONNX model, observations, PD gains, default pose, action scale
backendwhere commands go: MuJoCo, Unitree G1, RoboParty RP1 or a recorded replay
taskwhat the loop does around the policy; tracking adds reference motion

Where to go next​