nguyenphuminh/catniff
Torch-like deep learning framework for Javascript
Catniff is a deep learning framework designed for JavaScript developers that allows you to build, train, and apply neural networks directly within JavaScript environments. It takes numerical data (tensors) as input and outputs trained models or calculated gradients, enabling the creation of intelligent applications. This tool is for JavaScript developers who want to integrate machine learning capabilities into their projects without relying on Python-based frameworks.
Available on npm.
Use this if you are a JavaScript developer looking to implement deep learning models, such as text generators or custom neural networks, directly within your JavaScript projects using a familiar API.
Not ideal if you are a data scientist or machine learning engineer primarily working in Python, or if you require a mature, production-ready framework with extensive documentation and GPU acceleration.
Stars
8
Forks
1
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Jan 21, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nguyenphuminh/catniff"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
apache/tvm
Open Machine Learning Compiler Framework
uxlfoundation/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
Tencent/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
OpenMined/TenSEAL
A library for doing homomorphic encryption operations on tensors
iree-org/iree-turbine
IREE's PyTorch Frontend, based on Torch Dynamo.