tfjs and js-pytorch

These are competitors offering similar GPU-accelerated tensor computation and neural network training capabilities in JavaScript, though TensorFlow.js has significantly broader adoption and production readiness while js-pytorch provides a PyTorch-style API alternative.

tfjs
80
Verified
js-pytorch
40
Emerging
Maintenance 10/25
Adoption 25/25
Maturity 25/25
Community 20/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 14/25
Stars: 19,114
Forks: 2,022
Downloads: 1,313,493
Commits (30d): 0
Language: TypeScript
License: Apache-2.0
Stars: 1,222
Forks: 56
Downloads:
Commits (30d): 0
Language: JavaScript
License: MIT
No risk flags
Stale 6m No Package No Dependents

About tfjs

tensorflow/tfjs

A WebGL accelerated JavaScript library for training and deploying ML models.

Supports both browser and Node.js execution through pluggable backends (WebGL, WebAssembly, WebGPU, and native TensorFlow C++), enabling client-side inference and retraining with sensor data. Provides layered APIs from low-level linear algebra operations to high-level Keras-compatible layers, plus tools to import pre-trained TensorFlow and Keras models. Includes specialized packages for data processing, visualization, and AutoML model loading, with individual module imports available to minimize bundle size.

About js-pytorch

eduardoleao052/js-pytorch

A JavaScript library like PyTorch, with GPU acceleration.

Scores updated daily from GitHub, PyPI, and npm data. How scores work