#1 · Primary category: Robotics & Embodied AI Simulation

genesis-world

Simulation platform for general-purpose robotics & embodied AI learning.

Project last updated:08/29/26

GitHub Stars

29.8K

Forks

2.8K

Contributors

110

License

Apache-2.0

Why we included this project

Genesis World is a strong option for robotics and embodied-AI teams that want to test perception and control policies in simulation before touching real hardware. It wraps a unified multi-physics engine, a photorealistic renderer, and a cross-platform compiler in one Pythonic API, so you can build environments and generate synthetic training data, with parallel simulations that scale from a laptop to datacenter GPUs. Since the whole stack is Python, you can read and modify the simulator instead of treating it as a black box, which helps when you want to embed it in existing research code. The photorealism and speed, combined with the ability to dig into the code, make it a practical base for robot manipulation studies and large-scale synthetic data pipelines.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category