Opening the community workbench…
The community library
Skills, models, and the resources behind them. Follow an experiment from inspiration to your own workbench.
6 projects on this page
A simulated cap-to-tray task, adapted from NVIDIA's SO-101 workshop in Isaac Sim / Isaac Lab, uses a learned state-based PPO policy to generate 1,000 filtered LeRobot v3 demonstrations with top and wrist RGB. Simulation data generation; real-world transfer and SmolVLA improvement are not yet demonstrated.
A community SmolVLA fine-tune whose model card describes an SO101 orange-picking task in Isaac Sim.
A small LeRobot v3 dataset of MuJoCo SO101 demonstrations linked by the SO101-Nexus author.
XLeRobot shares hardware, software and simulation resources for a mobile robot built around SO100/SO101 arms.
LeRobot publishes a SmolVLA base model intended for fine-tuning on a specific robot task.
Official SO101 hardware designs and LeRobot assembly guidance for preparing a leader/follower setup.
Resources are contributed by the community. Availability of a model or dataset does not certify compatibility.
