# eduardoleao052/js-pytorch

A JavaScript library like PyTorch, with GPU acceleration.

Repository: https://github.com/eduardoleao052/js-pytorch
Canonical: https://ross.abutalabs.com/products/js-pytorch
Homepage: https://eduardoleao052.github.io/js-pytorch/site/index.html
Language: JavaScript
License: MIT
License Family: permissive
Topics: automatic-differentiation, deep-learning, javascript-library, neural-networks, pytorch
Last push: 2024-11-15T18:32:17+00:00

## Health v2 (maintenance only)
Score: 16/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 65
- inputs: {"age_days": 918, "days_push": 656, "days_rel": 672, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1222, forks 55 (observed 2026-08-28T04:04:02.402797+00:00)

## What it is
JS-PyTorch is a deep learning library for JavaScript that closely mirrors PyTorch's syntax, providing tensor operations, automatic differentiation, and neural network modules. It supports GPU acceleration via GPU.js and runs in Node.js or the browser.

## Use cases
- train neural networks in javascript
- run pytorch-style code in node.js
- build deep learning models in the browser
- automatic differentiation for javascript tensors
- gpu-accelerated tensor math in javascript
- deploy neural networks without python

## When to choose
- you want PyTorch-like syntax in a JavaScript environment
- you need to train or run neural networks in Node.js or the browser
- you want GPU acceleration for tensor operations in JS

## When to avoid
- you need production-scale training with mature ecosystem support
- you require advanced PyTorch features like distributed training or custom CUDA kernels
- your project is Python-based and can use PyTorch directly

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, gpu-computing
- domain: deep-learning, machine-learning, web-development
- platform: browser
- tags: pytorch, automatic-differentiation, neural-networks, tensor-operations, gpujs, nodejs, javascript

## Member repositories
- eduardoleao052/js-pytorch (main) score 16

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:02.402797+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:15:37.390522+00:00, confidence not recorded.
  - readme: https://github.com/eduardoleao052/js-pytorch (fetched 2026-08-28T04:04:02.402797+00:00, sha 265a6c417a53)
  - homepage: https://eduardoleao052.github.io/js-pytorch/site/index.html (fetched 2026-08-29T12:23:54.545458+00:00, sha 975d47314e80)
- Data as of 2026-08-30T08:39:29.467469+00:00.