client-side-ml

In-browser Singapore property valuation engine for HDB flats and private condominiums powered by dual XGBoost models (< 1ms JS inference). Features interactive transaction maps and two prediction modes: historical comparable valuation and index-adjusted forward projection.

Chrome extension that classifies Sentry errors with in-browser ML. Trains locally, learns from your corrections, zero backend.

SVG-native local AI companion powered by browser-side Transformers.js and ONNX. No Python backend, no hosted inference.

Run small LLMs directly in your web browser, no cloud computing needed.

A privacy-first, fully offline neural machine translation application supporting 200+ languages. Built on Meta's NLLB-200 model, this tool runs entirely in your browser without requiring server infrastructure or internet connectivity after initial model download.

Interactive student exam score & pass/fail predictor powered by client-side Linear and Logistic Regression.

An interactive, browser-based Real-Time Image Classifier using TensorFlow.js. Train a custom neural network entirely client-side using your webcam, complete with live predictions, model exporting.

Browser-based clothing classifier using a custom Teachable Machine model with entropy-based confidence filtering (the foundation for PICKyourFIT)

Real-time emotion detection and facial expression analysis web app powered by MediaPipe and ONNX Runtime. Features live webcam tracking and interview coach mode.

My portfolio and engineering journal. A statically generated Next.js site with an MDX writing section and a Lab of machine-learning experiments that run entirely in the visitor's browser, with no inference server behind them.

AI-powered personal finance dashboard, Auto-categorizes expenses, predicts spending trends, and provides intelligent insights.

Interactive UX concept exploring a portable pocket terminal in the browser using Svelte, TypeScript & Transformers.js. Features client-side AI chat (Qwen2.5-Coder via Web Workers/WebGPU), Conway's Game of Life with entropy metrics, live Bitcoin ASCII charting, and system diagnostics.