Awesome GitHub RepositoriesBrowser-Based Frameworks

Deeplearnjs is a JavaScript deep learning framework and automatic differentiation engine designed for building and training artificial intelligence models within a web browser environment. It functions as a machine learning library that leverages WebGL to provide hardware acceleration for neural networks. The project serves as a high-performance linear algebra library, using the GPU to execute operations on multi-dimensional arrays. This enables the implementation of deep learning models and the execution of client-side machine learning inference. The framework covers the complete automatic

Keras-js este un motor de inferență JavaScript și un framework de machine learning bazat pe browser, conceput pentru a executa rețele neuronale Keras pre-antrenate. Permite inferența modelelor client-side în browsere web sau medii Node.js, fără a necesita un server backend. Biblioteca utilizează un accelerator tensorial WebGL pentru a mapa operațiile matematice către procesorul grafic în vederea accelerării hardware. Pentru a menține responsivitatea interfeței utilizator în timpul calculelor grele, încorporează un runtime de inferență web worker care execută procesarea rețelei neuronale în thread-uri de fundal. Sistemul suportă încărcarea modelelor prin fișiere de configurare JSON și tensori de ponderi. Gestionează array-uri numerice mari folosind stocarea de texturi WebGL pentru a facilita accesul la memorie de mare viteză în timpul execuției tensoriale.

Docute is a browser-based documentation framework that transforms markdown files into functional websites directly within the user's browser. By performing all processing on the fly, it eliminates the need for static build steps, server-side compilation, or complex deployment pipelines. The platform functions as a single-page application, managing navigation and content updates dynamically by intercepting browser history events to avoid full page reloads. It utilizes a virtual file system abstraction to fetch and resolve documentation assets, ensuring that the site remains responsive and ligh

WebGPT is a browser-based machine learning framework designed to execute transformer models entirely within the client environment. By leveraging native web standards, it provides a zero-dependency runtime that enables local text generation without the need for backend server processing. The engine distinguishes itself by utilizing hardware-accelerated compute shaders to perform high-performance tensor computations directly on the user's graphics hardware. This approach allows for the execution of large language models locally, ensuring that all data processing remains private to the client d