Explore live open-source projects and AI models.

hxwgpu is a work in progress haxe/hxcpp wrapper around wgpu-native, allowing the use of the WebGPU API on desktop

Your AI now has a face. A pixel-art companion that reads LLM emotions in real time — 4 MB brain, WebGPU inference, zero cloud, 40+ characters. Plug in any LLM. Watch it feel hear and speak!.

A High performance and tiny TVM graph executor library written in C which can compile to WebAssembly and use CUDA/WebGPU as the accelerator.

Hardware-agnostic machine learning infrastructure for .NET. Implements high-performance neural network layers in C# that are transpiled to run on WebGPU, CUDA, OpenCL, WebGL, CPU, and Wasm via SpawnDev.ILGPU. Optimized for Blazor WebAssembly and native GPU execution.

WIP. Game engine written in TypeScript and Rust using WebGPU. Supports coop multiplayer. Will support visual coding and export to Steam. Focused on teaching and beginner friendliness.

⚙️ A work in progress ECS game engine

A React component for local, secure, on-demand translations powered by the Xenova/nllb-200-distilled-600M model. This package utilizes the WebGPU capabilities of the device on which the app runs, ensuring data privacy and enabling you to translate text without sending data to third-party APIs.

An implementation of MPM running in (near) real time in the browser utilizing the new WebGPU API.

This repository contains an experimental demo application that shows how you can add client-side auto-generated captions to Amazon IVS Real-time and Low-latency streams using transformers.js and WebGPU.

No description available from source.