# isaac-sim/IsaacLab

Unified framework for robot learning built on NVIDIA Isaac Sim

Repository: https://github.com/isaac-sim/IsaacLab
Canonical: https://ross.abutalabs.com/products/isaaclab
Homepage: https://isaac-sim.github.io/IsaacLab
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: robot-learning, robotics, omniverse-kit-extension, isaac-sim
Last push: 2026-08-26T21:07:43+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 79, longevity 99
- inputs: {"age_days": 1386, "days_push": 7, "days_rel": 62, "gap_med": 39.0, "n_releases_24m": 17}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7966, forks 3850 (observed 2026-08-28T04:10:10.314253+00:00)

## What it is
Isaac Lab is a GPU-accelerated open-source framework for robot learning built on NVIDIA Isaac Sim, unifying workflows like reinforcement learning, imitation learning, and motion planning. It provides accurate physics and sensor simulation (cameras, LIDAR, contact sensors) with 16+ robot models and 30+ ready-to-train environments.

## Use cases
- train reinforcement learning policies for robot manipulators
- simulate quadruped and humanoid locomotion on GPU
- run sim-to-real transfer experiments for robotics
- benchmark robot learning environments with RSL RL or SKRL
- generate sensor data like LIDAR and camera images in simulation
- scale robot training across cloud instances

## When to choose
- you need GPU-parallel physics simulation for robot learning
- you want prebuilt environments and robot assets for RL research
- you are doing sim-to-real transfer with NVIDIA Isaac Sim

## When to avoid
- you need lightweight simulation without NVIDIA Isaac Sim dependencies
- you only need simple 2D or non-robotics simulation
- you lack a GPU or NVIDIA hardware

## Facets
- artifact type: framework
- maturity: active
- function: simulation, machine-learning, reinforcement-learning, robotics, gpu-computing
- domain: robotics, reinforcement-learning, simulation, machine-learning, gpu-computing
- platform: windows, python
- tags: robot-learning, isaac-sim, sim-to-real, imitation-learning, motion-planning, sensor-simulation, humanoid-robots, linux, gpu

## Member repositories
- isaac-sim/IsaacLab (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:10.314253+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:32:36.716166+00:00, confidence not recorded.
  - readme: https://github.com/isaac-sim/IsaacLab (fetched 2026-08-28T04:10:10.314253+00:00, sha 67db3508de5c)
  - homepage: https://isaac-sim.github.io/IsaacLab (fetched 2026-08-29T08:29:40.309852+00:00, sha 0259b45b07f7)
- Data as of 2026-08-30T08:39:29.467469+00:00.