EmbodiedHub LogoEmbodiedHub
Back to Search
I

Isaac Lab

ProjectActive

Isaac Lab is a GPU-accelerated, open-source framework from NVIDIA designed to unify and simplify robotics research workflows, including reinforcement learning (RL), imitation learning (IL), and motion generation. In July 2026, Isaac Lab 3.0-beta2 was released with major improvements: kit-less operation (no Isaac Sim GUI required for RL training), multi-backend physics support (PhysX and Newton/Warp-native), browser-based live visualizers (Viser and Rerun), and 20+ ready-to-use preset environments including humanoids (Unitree H1, G1), quadrupeds, arms, and hands.

Details

Updated:7/30/2026
https://isaac-sim.github.io/IsaacLab
stars2500
languagePython
github urlhttps://github.com/isaac-sim/IsaacLab

Tags

multi-robotGPU-acceleratedsimulationrobotics-frameworksim-to-realNVIDIAIsaac-Sim3.0-beta2reinforcement-learningkit-less

Relationships

NVIDIA
Company
DEVELOPED_BY
Eureka
Model
USED_BY
ManiSkill2
Dataset
RELATED_TO
Isaac Sim
Project
DEPENDS_ON
NVIDIA Isaac GR00T
Project
SUPPORTS
ROS 2
Project
RELATED_TO
Isaac Sim
Project
SUPPORTS
MuJoCo
Project
USES
ManiSkill
Project
RELATED_TO
MuJoCo
Project
SUPPORTS

Sources

https://github.com/isaac-sim/IsaacLab
website
Visit
https://isaac-sim.github.io/IsaacLab
website
Visit
https://arxiv.org/abs/2511.04831
website
Visit

Appears In

Open Source Ecosystem

A collection of open-source projects and development tools that form the ecosystem for embodied AI and robotics research.

Embodied AI Landscape

An entry-point knowledge page providing an overview of the embodied AI ecosystem, including companies, robots, models, datasets, and open-source tools.