MacMimic trains humanoid motion controllers in 22 minutes on a MacBook Pro
KyleMorgenstein · x · 2026-11-20
MacMimic is an open-source (MIT) project that trains a simulated Unitree G1 humanoid to track 40 mocap clips — walking, sprinting, dancing, getting up, cartwheels — in just 22 minutes on a MacBook Pro (M4 Pro), no CUDA or cloud needed. MuJoCo simulates 4,096 robots on CPU cores while MLX trains on Apple GPU; each iteration takes 0.9s using a model-based approach (learn robot physics, then differentiate through it). It hits the benchmark target 2.04x faster than a BlinkMimic MLX port and 2.6x faster than XMimic. Full code and training pipeline are public, showing RL training for humanoid control can now run on consumer laptops.
More from Embodied
- DTMR tackles timing mismatch when legged robots imitate human motion — KyleMorgenstein · 2026-11-20
- Scoble: AI glasses mass adoption is 2-5 years away, BCI stays boring until then — Scobleizer · 2026-11-20
- Investor notes surge of BCI pitches, says core adoption problems remain unsolved — Scobleizer · 2026-11-20
- Framework shows off preproduction wireless touchpad keyboard — KevinNaughtonJr · 2026-11-20
- Demo: vision-only AI fire suppression system spotted on X — kscottz · 2026-11-20
- Figure's dancing robots spark debate: is tracker-based RL the wrong strategy? — KyleMorgenstein · 2026-11-20