Autograd for ndarray
Autograd Eigen backend
PyTorch-like JavaScript tensor/autograd library with CPU training support. Provides Tensor, autograd, nn.Module, Linear, Conv2d, Adam optimizer, and MNIST dataset utilities.
Tiny TypeScript-native tensor library with autograd, compiling to WebGPU. Train small models in the browser without hand-writing kernels, or run a pretrained one frozen for transfer learning.
Tensor computation and autograd with WebGPU acceleration
A tiny Autograd engine based off of Andrej Karpathy's micrograd in Python
PyTorch-like deep learning library for JavaScript — tensors, autograd, and neural networks in JS
A TypeScript ML framework with Rust native backends (CPU, CUDA, WebGPU) — autograd, tensors, and neural network training at GPU speed.
neurova AI core — Tensor (Float32Array) + reverse-mode autograd + nn layers/optim/losses. Pure TS, zero deps.
A simple, handrolled autograd implementation package with an MLP wrapper
A simple scalar autograd library for TypeScript
Autograd gpu.js backend
Tensor computation and autograd with WebGPU acceleration
A JavaScript/TypeScript autograd engine with operator overloading, inspired by micrograd
Scalar-based reverse-mode automatic differentiation in TypeScript.
Torch-like deep learning framework for Javascript
Forward + reverse-mode automatic differentiation for MathTS rank-N Tensor
Node.js bindings for NumRs
PyTorch like deep learning inferrence library
Tensor computation library with native and WASM backends
Internal native bindings - import from @mlx-node/lm or @mlx-node/trl instead
NumPy-inspired numerical computing for JavaScript with automatic Node N-API fallback to WebAssembly.
NumRs WebAssembly bindings for browser and Node.js
BrowserGNN by Dr. Lee - The World's First Comprehensive Graph Neural Network Library for the Browser
Tensors and differentiable operations in Rust
Rust CLI that generates GitHub Classroom autograder workflows for Rust assignments.
A command-line tool with an interactive TUI for fetching and exporting GitHub Classroom autograder results to CSV format.
Automatic differentiation module for SciRS2 (scirs2-autograd)
Automatic differentiation engine for TenfloweRS
Automatic differentiation engine for ToRSh with PyTorch-compatible API
Automatic differentiation engine for Axonml ML framework
A simple autograd library for learning purposes
A from-scratch deep learning library in Rust — tensors, autograd, NEON SIMD, Metal GPU, and working models
Automatic differentiation for GhostFlow ML framework
A Rust port of SciPy with AI/ML extensions - Scientific Computing and AI Library (scirs2)
Training & Optimization library with autograd, LoRA, quantization, and model merging
ignis-autograd adds a differentiable tensor (Ignis::Tensor) and a reverse-mode autograd tape on top of the Ignis GPU foundation. Build computation graphs over GPU arrays and get exact gradients (verified against finite differences). The building block for neural-network training in pure Ruby on an NVIDIA GPU.
Ruby implementation of karpathy/micrograd
ignis-dl is the deep-learning layer of the Ignis ecosystem: NN modules (Linear, Embedding, LayerNorm, RMSNorm, Dropout), optimizers (SGD/Adam/AdamW), losses, and a transformer stack (multi-head + grouped-query attention, RoPE, SwiGLU, KV cache) with HuggingFace weight loaders (GPT-2, Llama). Loads real GPT-2 and Llama-3.2 checkpoints and matches HuggingFace logits, and trains transformers from scratch — in Ruby, on native Windows. Installing this pulls the whole stack (ignis + ignis-autograd), so it also serves as the meta-gem.
GRX brings PyTorch-style tensor operations to Ruby. Every arithmetic op, activation, and optimizer step runs through a native C library compiled with AVX2+FMA SIMD. Ruby is the interface — C does the work. Features: autograd, SGD/Adam optimizers, Linear/Sequential/Dropout/BatchNorm layers, MSE/BCE/CrossEntropy loss functions, Xavier and He weight init. Cross-platform: .so on Linux, .dylib on macOS, .dll on Windows.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.