SO-101 (SO-ARM101)

Low-cost 3D-printable 6-DOF leader/follower arm pair built for Hugging Face's LeRobot framework; successor to the SO-100 with improved wiring and easier assembly.

Frames · SO-101 (SO-ARM101)

4 items · credit and license on each

Studio render of the published MJCF, the model's zero pose. Geometry only; colours are the model's own materials.Rendered by Hyperspawn from mujoco_menagerie/robotstudio_so101 (Apache-2.0) · Hyperspawn render · source
Side view of the same MJCF render, the model's zero pose.Rendered by Hyperspawn from mujoco_menagerie/robotstudio_so101 (Apache-2.0) · Hyperspawn render · source
4 s turntable of the MJCF studio render.Rendered by Hyperspawn from mujoco_menagerie/robotstudio_so101 (Apache-2.0) · Hyperspawn render · source
From the SO-ARM100 repo media folder.The Robot Studio (SO-ARM100) · Apache-2.0 · source

Provenance

No browser-ready model packaged yet.

The description is public, but nobody has pinned a commit and checked it compiles in MuJoCo WASM. Clone it and drop the folder on the viewport above (MJCF, or URDF with STL/OBJ meshes). Files stay in your tab.

Policies listed for SO-101 (SO-ARM101)

Generalist SO-101 pick and place (world action model, fine-tune with the included LoRA recipe)
LeRobot (Flux3Policy) · not replayed in the tab
source
SO-100/101 language-conditioned manipulation (VLA, zero-shot or fine-tune)
LeRobot (MolmoAct2) · not replayed in the tab
source
SmolVLA base (pretrained VLA to fine-tune on your own SO-101 dataset)
LeRobot (SmolVLA) · not replayed in the tab
source

Train on GPUs

mjlab ships no stock task for SO-101 (SO-ARM101). The training page gives you the pinned model and the steps to write a robot config.

Build the job →