ReLU, the rectified linear unit
Reusable ECS core engine for Relu Spatial editor and runtime experiences.
RELU快速开发平台bpmn组件
RELU快速开发平台报表
Core for bot
Rectified linear unit non-linearity
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.
GPU accelerated neural networks made simple for Javascript
Node-API bindings for MLX
GPU Javascript Library for Machine Learning
neurova AI core — Tensor (Float32Array) + reverse-mode autograd + nn layers/optim/losses. Pure TS, zero deps.
Neural tabular models (MLP, TabM, NAM) for wlearn via polygrad
Zero-code runtime observability for JS/Python + AI agent debugging. Traces LangChain, CrewAI, OpenAI, Anthropic, Gemini. Eval, security, compliance, cost tracking. Free, local-first.
神经网络架构可视化工具 - 输入 YAML 格式的网络定义，生成 SVG 架构图
A lightweight, zero-dependency Neural Network and Matrix math library.
Bayesian probability transforms for BM25 retrieval scores
NeuralNetwork with pure Javascript
A piecewise function factory
evo-tf allows for easy neuro-evolution in the browser using tensorflow.js This project is not 100% finished and has some areas I still need to touch up on. But you can expect it to be ready within the next couple days, possibly the 17th. There will also
ConvNetJS is a Javascript implementation of Neural networks.
No description provided.
GPU Powered Neural Networks for every Browser
A simple artificial neural network
A simple feed-forward Neural Network implementation in ES6 JavaScript
No fluff bindings to Luau.
ReLU en virgule fixe Q15 pour systèmes embarqués `no_std`, zéro dépendance
This is rssn-advanced: The next generation symbolic core of rssn.
Safe Rust. No Deps. RL for the CPU.
Kernel fusion optimization for the Axonml ML framework
A minimal, verifiable ONNX runtime implementation in Rust
This is a collection of activation functions
Fast neural network primitives for Lattice - tiny models, fast inference
A numpy-like library for Rust
ONNX runtime with 128+ operators, quantization, and graph optimization
Instruction-based neural network model training library using Burn
Micro Managed Neural Network
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.