Robots Atlas>ROBOTS ATLAS
ONNX Runtime

Other · Artificial Intelligence / ML

ONNX Runtime

v1.29.0·Microsoft

Active Open source API available
CATEGORYOther · Artificial Intelligence / ML
READINESSTRL 9
ADOPTION SCALEWidespread adoption
LICENSESMIT
FIRST RELEASE2018

ONNX Runtime is an open-source, cross-platform accelerator for inference and training of machine-learning models stored in the ONNX (Open Neural Network Exchange) format. The project is developed and maintained by Microsoft and released under the MIT license.

Its core is written in C++, with official APIs available for Python, C#/.NET, Java and JavaScript, among others. The engine runs on Linux, Windows, macOS, iOS and Android as well as in the browser, across environments from cloud to edge and mobile devices.

Performance comes from pluggable execution providers that leverage hardware acceleration: CPU, NVIDIA CUDA and TensorRT, DirectML (Windows), Apple CoreML, Intel OpenVINO, Qualcomm QNN and others. ONNX Runtime powers Microsoft products including Windows, Office, Azure services and Bing.

WebsiteDocumentationRepository
Type & Roles
Software types
Inference Runtime

An inference runtime loads a pre-trained model and runs forward passes (predictions) on input data. It typically supports hardware acceleration (CPU, GPU, NPU) through pluggable execution backends.

Machine Learning Library

A software library exposing APIs to build, deploy or execute machine-learning models within applications.

Select an item to see its description.
Main category
Artificial Intelligence / ML
Maturity & Adoption
9 / 9
Proven in operational conditions
ResearchPrototypeProduction
Adoption scaleWidespread adoption
Maintenance statusActively maintained
First release2018
Last update25 August 2026
Deployments

Used in Windows, Microsoft Office, Azure services and Bing.

Community

Over 21,000 GitHub stars and ~4.2k forks (microsoft/onnxruntime).

Organizations
System capabilities
⊙
Open source
Source code is publicly available under an open-source license — enables security audits, custom modifications, and integration without licensing barriers.
✓
⚡
Real-time capable
Designed with timing-determinism guarantees — meets the requirements of control loops, safety systems, and tasks demanding low, predictable latency.
×
⟨/⟩
API available
The software exposes a programmable interface (REST, gRPC, SDK, or language bindings) that enables automation and integration with other systems.
✓
📦
Pre-built / binary
Distributed as ready-to-use binary packages, container images, or installers — no need to build from source.
✓
Programming languages
C++

A compiled, high-performance, general-purpose programming language. The primary implementation language of the ONNX Runtime core.

Python

A high-level interpreted language dominant in machine learning. ONNX Runtime provides an official Python API.

C#

An object-oriented programming language by Microsoft for the .NET platform. ONNX Runtime provides an official C#/.NET API.

Select an item to see its description.
Operating systems
Linux

A family of open-source operating systems based on the Linux kernel, common on servers, in the cloud and in robotics.

Windows

Microsoft's family of operating systems for personal computers and servers.

macOS

Apple's operating system for Mac computers.

iOS

Apple's mobile operating system for iPhone and iPad devices.

Android

A mobile operating system based on the Linux kernel, developed by Google.

Select an item to see its description.
Minimum hardware requirements
Packaging & distribution
Package managers
pip (PyPI)

The Python package manager. The onnxruntime package is distributed via PyPI.

NuGet

The package manager for the .NET platform. ONNX Runtime ships as Microsoft.ML.OnnxRuntime packages.

npm

The package manager for the JavaScript/Node.js ecosystem. The onnxruntime-web and onnxruntime-node packages are distributed via npm.

Maven

A dependency and build manager for the Java ecosystem. ONNX Runtime is distributed as com.microsoft.onnxruntime.

Select an item to see its description.
CPU architectures
x86-64

A 64-bit CPU architecture compatible with the x86 instruction set, dominant in PCs and servers.

ARM64

A 64-bit ARM CPU architecture, common in mobile, embedded and increasingly server devices.

Select an item to see its description.
Installation difficulty
LevelEasy
Protocols and interfaces
Deployment types
Cloud

Deployment in a cloud environment (servers, containers, managed services).

Edge / on-device

Local deployment on an edge or embedded device, without cloud dependency.

Mobile

Deployment on mobile devices (iOS, Android).

Web / browser

Execution in a web browser (e.g. via WebAssembly / WebGPU).

Select an item to see its description.
Licenses
MITMIT License
ModificationDistributionCommercial useSublicensingPrivate useROS-compatibleOSI approvedFSF Free/LibreRequires attribution

A permissive free-software license originating at the Massachusetts Institute of Technology. It permits use, copying, modification, merging, publishing, distribution, sublicensing and sale of the software, provided the copyright notice and license text are preserved. It has no copyleft.

Robotics note

A permissive license fully compatible with the ROS/ROS 2 ecosystem and with closed-source commercial products.

Official text ↗SPDX ↗OSI ↗
Version history
v1.29.0Aug 2026

Latest stable release in the 1.x series.

v1.0.0Oct 2019

First stable 1.0 release (general availability).

v0.1.4Nov 2018

First public release of ONNX Runtime as an open-source project.