Rigyd
Turn images into simulation-ready assets in minutes
Rigyd is an AI-native 3D infrastructure platform that converts raw 3D models, images, and text into physics-enabled OpenUSD and MJCF assets for robotics simulators like NVIDIA Isaac Sim, MuJoCo, Gazebo, and Unreal Engine. The platform automatically adds collision meshes, mass, friction, and semantic labels without requiring manual annotation or physics expertise. It targets robotics teams that need scalable, physics-accurate simulation data for training embodied AI systems.
Users upload 3D models, images, or text descriptions; the platform's AI generates or optimizes geometry, estimates physical properties, and outputs validated OpenUSD assets ready for major simulators.
Robotics engineers and AI teams building simulation data pipelines for embodied AI
Background.
- Status
- launched
- Business model
- freemium
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.