sonos/tract

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

67
/ 100
Established

This is a neural network inference toolkit that helps you run trained AI models in production environments. It takes models saved in formats like ONNX or NNEF and efficiently executes them, providing predictions or classifications. It's designed for engineers deploying AI models into applications, especially on resource-constrained devices, or those looking to optimize model performance.

2,818 stars. Actively maintained with 237 commits in the last 30 days.

Use this if you need to run pre-trained machine learning models quickly and efficiently in an application, converting models from training frameworks like TensorFlow or PyTorch into a deployable format.

Not ideal if you are looking for a tool to train neural networks or if your models heavily rely on advanced ONNX features like Tensor Sequences and Optional Tensors.

AI-model-deployment edge-AI ML-inference embedded-systems production-AI
No Package No Dependents
Maintenance 22 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

2,818

Forks

250

Language

Rust

License

Last pushed

Mar 13, 2026

Commits (30d)

237

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sonos/tract"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.