Automated Android “Find The Sets” game solver using OpenCV + ADB + Python.

Lightweight JavaScript library that predicts user intent based on mouse movements and keyboard navigation. Perfect for smart prefetching. Also works for mobile!

SnapDOM is a next-generation DOM capture engine that transforms HTML into almost any format all powered by a flexible plugin system

webgpu for node.js

Diffusion model(SD,Flux,Wan,Qwen Image,...) inference in pure C/C++

Desktop environment in the browser

A music theory library for Javascript

A JavaScript library like PyTorch, with GPU acceleration.

Automatic colorization for gray scale (images/ videos) based on Deep-Learning using (Python & Tensorflow)

PyTorch code and models for V-JEPA self-supervised learning from video.

A mini library for Policy Gradients with Parameter-based Exploration, with reference implementation of the ClipUp optimizer (https://arxiv.org/abs/2008.02387) from NNAISENSE.

Draw a ui and make it real

Draw a mockup and generate html for it

jMuxer - a simple javascript mp4 muxer that works in both browser and node environment.

MP4 multiplexer in pure TypeScript with support for WebCodecs API, video & audio.

ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering

The code for the bark-voicecloning model. Training and inference.

Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.

⚡️ TypeScript Execute | The easiest way to run TypeScript in Node.js

Tiny AutoEncoder for Stable Diffusion

Syntax highlighting for WGSL inside JavaScript tagged template strings

📹 Recorder | Open-source web app to record screen and camera directly in your browser | No installation required | No tracking | Fully local | 🚀

JavaScript version of GPAC's MP4Box tool

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Upload a single page application to S3 with the right content-type and cache-control meta-data

wasm bindings for huggingface tokenizers library

showing various ways to serve Keras based stable diffusion

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.