NVIDIA Isaac Lab
Project record
Isaac Lab is an open-source, GPU-accelerated framework for robot learning built on NVIDIA Isaac Sim. It provides robot models, ready-to-train environments, sensor simulation, and workflows for reinforcement learning, imitation learning, and motion planning. Its technical report describes it as the successor to Isaac Gym; its development started from the Orbit framework.178
- Repository: GitHub repository (external site: github.com)
- Documentation: Documentation (external site: isaac-sim.github.io)
- Website: NVIDIA Isaac Lab developer page (external site: developer.nvidia.com)
- Paper: Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning (arXiv 2511.04831) (external site: arxiv.org)
- License: LICENSE (BSD-3-Clause) (external site: github.com)
- Release notes: Release v3.0.0-EA (external site: github.com)
Availability and license
Overall availability
Source code is public on GitHub. Full-featured workflows (PhysX, RTX rendering, ROS, URDF and MJCF importers) require NVIDIA Isaac Sim, which includes components under proprietary terms; the README says Kit-less Newton workflows do not require Isaac Sim.1
Availability is separate from permission: read the license before using or redistributing.
Apache License 2.0 (isaaclab_mimic extension and its standalone scripts) (external site: github.com)31
The framework is BSD-3-Clause, while the isaaclab_mimic extension and its standalone scripts are Apache 2.0. The README notes that Isaac Sim includes components under proprietary terms and that isaaclab_mimic requires cuRobo, which also has proprietary terms; license files for dependencies and assets are kept in the repository's docs/licenses directory.123
Component reuse rights
- weights
- Unknown — no complete fact-level rights review
- code
- Terms or license combinations require review
- data
- Unknown — no complete fact-level rights review
- documentation
- Unknown — no complete fact-level rights review
No complete system-rights review is recorded for this release.
Public materials checklist
| Item | Status | Notes and evidence |
|---|---|---|
| Source codeIs the source code publicly readable? | Public | Developed in the public isaac-sim/IsaacLab GitHub repository.1 |
| DocumentationIs user documentation published? | Public | Versioned documentation covers installation, tutorials, how-to guides, environments, and API reference.8 |
| InstallationAre installation instructions or packages publicly available? | Public | The installation guide documents pip, binary-plus-source, full source, pip-only, and Docker methods; Isaac Sim must be installed first for workflows that depend on it.9 |
| Supported platformsAre supported operating systems or hardware documented? | Public | The main-branch guide lists Ubuntu 22.04 (Linux x64) or Windows 11 (x64), at least 32 GB RAM and 16 GB GPU VRAM, and describes limitations on aarch64 DGX Spark. Isaac Lab 3.0 targets Isaac Sim 6.1 and Python 3.12.91 |
| Release statusAre versioned releases published? | Public | The Orbit project page dates the official Isaac Lab release to June 2024 (an update marked 03.06.2024). Versioned releases are tagged on GitHub. Isaac Lab 3.0 Early Access (v3.0.0-EA) was published on September 16, 2026; the 2.3.x line (isaaclab 2.3.2.post1 on PyPI) supports Isaac Sim 4.5 to 5.1.1011112 |
What it is useful for
Organization context
Provenance and derivatives
Isaac Lab development started from the Orbit framework, whose project page lists authors affiliated with ETH Zurich, NVIDIA, and the University of Toronto and says Orbit continued as Isaac Lab. NVIDIA's technical report presents Isaac Lab as the successor to NVIDIA Isaac Gym. Full-featured workflows depend on NVIDIA Isaac Sim, which includes proprietary components.1712
- Derived from: Orbit (external site: isaac-orbit.github.io) — Framework from which Isaac Lab development started, per the README and the Orbit project page.
U.S. eligibility
Eligible · basis: U.S.-governed project
Multi-organization assessment. The CONTRIBUTORS file lists four developer organizations: NVIDIA Corporation & Affiliates, Boston Dynamics AI Institute, ETH Zurich, and the University of Toronto, and the copyright is held by "The Isaac Lab Project Developers". Direction and distribution are documented as NVIDIA's: the repository is hosted in the NVIDIA Isaac Sim GitHub organization, NVIDIA distributes it as "NVIDIA Isaac Lab" on its developer site, and the technical report is published under NVIDIA's name, with all three members of its "core leadership" (defined as having primary responsibility for organizational and technical direction) listed with NVIDIA affiliations. NVIDIA's principal executive offices are in Santa Clara, California, per its Form 10-Q for the quarter ended July 26, 2026. No separate governance charter was found.4256713
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.