#8787th of 206 in ML frameworks and librariesFor science, health and research, robotics
isaacsim
NVIDIA robotics simulator on Omniverse with RTX sensors and GPU physics
- Stars
- 4.5k
- License
- custom license
- Last commit
- Nov 2026
- Last release
- Oct 2026
- Language
- Python
3,027 on 22 Apr 20264,469 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Isaac Sim is a robot simulator built on NVIDIA Omniverse. It imports robots from URDF, MJCF and CAD, and simulates them with GPU-accelerated physics and RTX-rendered sensors. It includes ROS 2 integration, synthetic data generation and Isaac Lab for reinforcement and imitation learning. It is built from source with build.sh or build.bat, or installed as Python wheels from pypi.nvidia.com.
Who it is for: Robotics engineers simulating robots and generating training data on NVIDIA GPUs
Strengths
- Imports URDF, MJCF and CAD robot descriptions for simulation
- Covers RL, synthetic data generation and ROS bridge in one platform
- Runs on Linux x86_64, Linux aarch64 and Windows; pip wheels for releases
- Docs include quickstart tutorials and a USD asset catalog
Weaknesses
- Needs an RTX-class GPU; stated minimum is an RTX 4080 or A40
- Linux build requires GCC/G++ 11; newer compilers are unsupported
- Build downloads Omniverse Kit SDK and extensions, so internet access is required
- First launch can take several minutes while extensions and shaders cache
What it needs
- GPU required
- Needs NVIDIA Omniverse Kit SDK, Git LFS, GCC/G++ 11 (Linux), Visual Studio 2022 (Windows C++), NVIDIA driver, Python 3.12
- Models: URDF, MJCF, CAD, USD
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in ML frameworks and libraries
See all 206| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |