Newton Physics Engine
SoftwareLinux Foundation GPU-accelerated, differentiable robotics physics engine built on NVIDIA Warp with MuJoCo Warp and OpenUSD support, licensed under Apache-2.0 (code) and CC-BY-4.0 (docs). [2] [3]
Installation & first result →Official websiteSource codeGetting started
- For
- Robotics simulation researchers; RL and sim-to-real engineers; Physics engine and differentiable-control developers [2] [4]
- Hardware
- NVIDIA Turing+ GPUs (compute capability 7.5+, driver R580+ for Warp 1.18+), CPU fallback (including macOS) [2]
- Source rights
- Named licenses are documented by part. Review licenses
Source researched · Not tested by us
Sources checked · Research details
Licenses & related hardware
- Ecosystem
- MuJoCo
- License
- Apache-2.0, CC-BY-4.0 · Details by part
Overview
Newton is a Linux Foundation GPU-accelerated, differentiable physics engine for robotics built on NVIDIA Warp, initiated by Disney Research, Google DeepMind, and NVIDIA. It generalizes Warp's deprecated warp.sim module, uses MuJoCo Warp as its primary articulated-body backend, and adds native OpenUSD and URDF workflows. GitHub release metadata records v1.8.0 on 2026-11-11, while the README and pyproject.toml inspected in this review come from main commit ab4af1502ab9340bb5946665311da0d43795246c (checked 2026-11-21), which declares version 1.9.0.dev0. Because the v1.8.0 manifest was not separately inspected, attribute the requirements and optional extras below to that main checkout and check the v1.8.0 release metadata before assuming identical pins on PyPI. [1] [2] [4]
Is this for you?
- Workflows
- Install modular extras ([sim], [importers], [examples]) via pip or uv
- Load URDF or OpenUSD scenes and simulate on GPU via MuJoCo Warp
- Record and replay trajectories with built-in viewers
- Run ONNX neural actuators / RL policy examples
- Known limitations
- CUDA acceleration with Warp 1.18+ requires an NVIDIA Turing GPU (compute capability 7.5+) and driver R580+ (older R545–R579 drivers require pinning warp-lang==1.17.0); macOS runs on CPU only.
- Base pip install newton only installs warp-lang>=1.17.0; MuJoCo Warp (newton[sim]), USD/mesh importers (newton[importers]), and viewer/examples (newton[examples]) are separate optional extras with platform/Python constraints (e.g., warp-optix is restricted to Python 3.12 on Linux/Windows x86_64).
- Simulation throughput, differentiability convergence, and third-party community solvers were not benchmarked in this review.
What you need
- Operating system
- Linux (x86-64, aarch64)
- Windows (x86-64)
- macOS (CPU only)
- Dependencies
- Python >=3.11
- warp-lang>=1.17.0
- Optional [sim]: mujoco-warp~=4.0.1, mujoco-core~=4.0.1
- Optional [importers]: usd-core, newton-usd-schemas>=0.7.0, trimesh, coacd, resolve-robotics-uri-py
- Optional [onnx]: warp-nn[onnx]~=0.4.0
- Host computer
NVIDIA Turing GPU (compute capability 7.5+) with driver R580+ for CUDA acceleration with Warp 1.18+ (or warp-lang==1.17.0 on R545–R579); no local CUDA Toolkit required; macOS runs on CPU only.
- Compute for the workload
- NVIDIA Turing GPU (compute capability 7.5+) and driver R580+ for Warp 1.18+ CUDA wheels (or warp-lang==1.17.0 on R545–R579)
- CPU-only execution supported on macOS
Installation & first result
Open the upstream getting-started guide [2] · Project documentation [1] [2]
- Verify Python 3.11+ and (for CUDA) an NVIDIA Turing+ GPU with driver R580+ (or pin warp-lang==1.17.0 on R545–R579 drivers; no local CUDA Toolkit required).
- Install Newton with examples via pip install "newton[examples]" (or select minimal extras such as newton[sim] and newton[importers]).
- Inspect example specifications without executing them via python -m newton.examples --describe robot_omniwheel, or run python -m newton.examples basic_urdf.
Hardware, models & data
- Supported hardware
- NVIDIA Turing+ GPUs (compute capability 7.5+, driver R580+ for Warp 1.18+)
- CPU fallback (including macOS)
- Interfaces
- Python API (newton)
- CLI example runner (python -m newton.examples)
- OpenGL viewer (pyglet / imgui_bundle) and recording/replay viewer
- URDF and OpenUSD scene importers
- Inputs and outputs
Loads URDF, OpenUSD, and mesh assets into GPU-accelerated Warp/MuJoCo Warp simulation models; outputs physics state trajectories, OpenGL/recording viewer streams, and binary CBOR recordings.
- File formats
- OpenUSD (usd-core, newton-usd-schemas)
- URDF
- Mesh formats (trimesh, meshio, COLLADA .dae)
- CBOR binary recordings (.bin)
- ONNX policy models (via [onnx] extra)
- Algorithms and models
- MuJoCo Warp articulated-body physics backend
- NVIDIA Warp differentiable simulation kernels
- Optional ONNX policy inference (warp-nn[onnx])
- Evaluation
Built-in example runner supports inspecting descriptions and success criteria via python -m newton.examples --describe <name>; not executed in this review.
Project notes
GPU driver floors and OS limits
Newton requires Python 3.11+ and runs on Linux (x86-64, aarch64), Windows (x86-64), and macOS (CPU only). No local CUDA Toolkit installation is required, but CUDA acceleration has an important driver threshold: starting with Warp 1.18, standard Warp wheels require an NVIDIA Turing GPU (compute capability 7.5+) and driver R580+. On older supported GPUs or hosts running drivers R545–R579, upstream instructs pinning warp-lang==1.17.0. [2]
Core package vs. optional extras in pyproject.toml
A bare pip install newton only pulls warp-lang>=1.17.0. Most robotics workflows require opting into specific extras declared in pyproject.toml: [4]
[sim]: pullsmujoco-warp~=4.0.1andmujoco-core~=4.0.1(excluded on Windows ARM64).[importers]: pullsusd-core/usd-exchange(with Python-version andaarch64wheel markers),newton-usd-schemas>=0.7.0,trimesh,coacd,scipy, andresolve-robotics-uri-pyfor local-file, package, and model robotics URIs.[onnx]: pullswarp-nn[onnx]~=0.4.0for neural actuators and RL policy examples.[optix]: pullswarp-optix~=0.3.0for hardware-accelerated camera traversal, currently restricted to Python 3.12 on Linux/Windowsx86_64.[examples]: bundles[sim],[importers],[onnx],pyglet,imgui_bundle,GitPython(fornewton.utils.download_asset()), andcbor2binary recordings.
Every bundled example embeds its description and success criteria, which you can inspect before executing anything via python -m newton.examples --describe robot_omniwheel (or uv run --extra examples -m newton.examples ... from a source checkout). [2]
What we checked
Primary-source repository metadata, README, LICENSE.md, and pyproject.toml inspection only. No Python environments were created, no GPU kernels were compiled, and no simulation examples were run.
Updates
Source files and licenses
Flagship Linux Foundation GPU-accelerated robotics physics engine with verified Apache-2.0 code and CC-BY-4.0 documentation licensing.
| Layer | Availability / license |
|---|---|
| software | available · Apache-2.0 Code licensed under Apache-2.0; additional third-party license texts are bundled in newton/licenses/. [2] [3] [4] |
| documentation | available · CC-BY-4.0 README explicitly declares Documentation is licensed under CC-BY-4.0. [2] |
Physics simulation engine; no pretrained model weights distributed as core artifacts.
Physics simulation engine; no standalone datasets distributed.
Apache-2.0 code and CC-BY-4.0 documentation licensing
Newton separates its code and documentation rights: source code is licensed under Apache-2.0 (LICENSE.md), documentation is designated CC-BY-4.0 in the README, and bundled third-party license texts are collected under newton/licenses/. Under the supplied Apache-2.0 text, redistributions must include a copy of the license, carry prominent notices on modified files, retain applicable copyright, patent, trademark, and attribution notices in source-form distributions of derivative works (excluding notices that do not pertain to any part of the derivative works), and include applicable NOTICE attributions when distributing derivative works if the original includes a NOTICE file. The full CC-BY-4.0 legal text was not included or reviewed in this packet, so consult it directly before redistributing documentation. External community solvers tagged with newton-physics on GitHub are explicitly unendorsed and maintain their own licenses and support levels. [2] [3] [4]
No Python packages were installed, no Warp GPU kernels were compiled, and no simulation examples were executed in this review. The next step is verifying your host NVIDIA driver version (R580+ for Warp 1.18+, or pinning warp-lang==1.17.0 on R545–R579 drivers or older supported GPUs), installing newton[examples] in a Python 3.11+ environment (noting that compatibility between released PyPI packages and the inspected 1.9.0.dev0 development manifest has not been established here), and running python -m newton.examples basic_urdf to confirm local rendering and backend execution. [2] [4]
References
Each source links to the exact revision we read. “Used for” shows where this page relies on it.
- S001 newton-physics/newton repository metadata, v1.8.0 release, and HEAD commit
Confirms Apache-2.0 license, v1.8.0 release on 2026-11-11, and active commits through 2026-11-21.Revision, date & where cited
Newton Developers (Linux Foundation) · github.com · revision
ab4af15· main HEAD (2026-11-21); release v1.8.0 (2026-11-11) · Accessed Nov 21, 2026
Used for: Overview, Installation & first result, What we checked - S002 newton-physics/newton README.md
Documents Linux Foundation governance (initiated by Disney Research, Google DeepMind, NVIDIA), NVIDIA Warp and MuJoCo Warp backend, OpenUSD support, Python 3.11+, Turing GPU / R580+ driver requirement (or warp-lang==1.17.0 for R545-R579), macOS CPU-only mode, Apache-2.0 code and CC-BY-4.0 docs licensing, and quickstart commands.Revision, date & where cited
Newton Developers (Linux Foundation) · github.com · revision
ab4af15· README.md at · Accessed Nov 21, 2026
Used for: Overview, Is this for you?, What you need, Installation & first result and 4 more - S003 newton-physics/newton LICENSE.md
Apache License 2.0 covering Newton source code.Revision, date & where cited
Newton Developers (Linux Foundation) · github.com · revision
ab4af15· LICENSE.md at · Accessed Nov 21, 2026
Used for: Source files and licenses - S004 newton-physics/newton pyproject.toml
Declares requires-python >=3.11, core dependency warp-lang>=1.17.0, optional extras sim (mujoco-warp~=4.0.1, mujoco-core~=4.0.1), importers (usd-core, newton-usd-schemas>=0.7.0, trimesh, coacd, resolve-robotics-uri-py), onnx (warp-nn[onnx]~=0.4.0), optix, remesh, and examples.Revision, date & where cited
Newton Developers (Linux Foundation) · github.com · revision
ab4af15· pyproject.toml at · Accessed Nov 21, 2026
Used for: Overview, Is this for you?, What you need, Installation & first result and 3 more
Correction guidance · Discussion is not enabled · Profile format 0.8.0-draft.1