Skip to main content
Frameworkai-frameworksvN/A

ONNX Runtime

by Microsoft · open-source · Last verified 2026-03-24

ONNX Runtime is a cross-platform, high performance scoring engine for Open Neural Network Exchange (ONNX) models. It is designed to accelerate machine learning inferencing across a wide range of hardware and operating systems, optimizing model execution for speed and efficiency.

https://onnxruntime.ai/
B+
B+Good
Adoption: AQuality: A+Freshness: B+Citations: B+Engagement: B

Specifications

License
MIT License
Pricing
open-source
Capabilities
model-optimization, hardware-acceleration, cross-platform-deployment, quantization
Integrations
TensorFlow, PyTorch, scikit-learn, CUDA, DirectML
Use Cases
image-recognition, natural-language-processing, speech-recognition, recommendation-systems
API Available
Yes
Tags
inference, cross-platform, optimization, onnx
Added
2026-03-24
Completeness
100%

Index Score

77.2
Adoption
80
Quality
90
Freshness
75
Citations
70
Engagement
65

Put AI to work for your business

Deploy this framework alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.

Explore the full AI ecosystem on Agents as a Service