in-browser-ml

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

Browser-side RAG demo — runs embeddings entirely in the browser via transformers.js (@xenova), no backend. React + Vite + TypeScript.

In-browser custom vision-AI detector.

Bilingual (English + Bangla) sentiment analysis platform that runs entirely in your browser. Features an explainable rule-based engine, real in-browser ML training (LR / NB / SVM) with confusion matrix and per-class F1, live visualizations, and an optional hardened LLM chat. Offline-first, built with React + TypeScript.

Paste any text and watch a neural network be born in your browser tab and learn to speak like you. No API, no server — it trains on your own GPU and dies when you close the page.

An AI that teaches itself to drive — a PPO-trained Transformer running live in your browser (WebGPU), where you can also wipe the brain and watch a new network learn from scratch. No hand-coded rules.

⚡ MoX + WebGPU: a tiny, zero-dependency WebGPU compute (GPGPU) framework — typed tensors, raw WGSL kernels, and a lazy compute graph.

Real-time, in-browser facial expression reader with calibrated confidence, literature-grounded cognitive states, and FACS-grounded AI explanations.

Build hand gesture datasets from your webcam and train a classifier right in your browser. MediaPipe 3D hand tracking + TensorFlow.js. Export to ZIP, CSV, or a TF.js model. All data stays on your device.