seehiong
@seehiong
Always learning, sometimes breaking, forever caffeinated! PyTorch | TensorFlow | LangChain | MLflow | KubeFlow | Neural Networks | Kubernetes
Activity
53 recorded weeks342 contributions in the last year · 185 in 90 days
Public contributions, including anonymous private activity shared on GitHub.
Velocity: 0.5 contributions per day over the past 30 days
TypeScript61%
HTML21%
Python9%
JavaScript9%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.
NoteFlow Studio — a web-based music IDE and synthesizer. Compose multi-track songs in simple text notation, play via QWERTY or MIDI keyboard, record performances, and co-write with an AI assistant. Realistic Web Audio instrument modeling: piano, organ, flute, violin, cello, and drums. Built with React, TypeScript, and Vite
Markdown Editor Pro — A powerful, feature-rich markdown editor with live preview, LaTeX math support, GitHub-inspired styling, and seamless integration into React apps. Built with React, TypeScript, and Tailwind CSS.
Multi-Model Chat — Compare responses from multiple AI models side by side in real-time. Supports GPT, Claude, Mistral, and local models (Ollama). Built with React, TypeScript, and Tailwind CSS.
Private-by-design ATS resume analyzer that runs entirely on your machine via WebLLM or local Ollama. Match scores, missing keyword detection, and AI resume rewrites with zero server uploads.
TextForge — A modern web toolkit for text processing, code formatting, regex testing, time conversion, Lorem Ipsum generation, encoding, hashing, and utility generation. Built with React, TypeScript, and Tailwind CSS.
seehiong.github.io Tech Blog
Automate Blender 3D modeling with AI via MCP — 93 tools for modeling, sculpting, architecture/MEP, materials, and 3D-print prep. Includes Blender Studio: a visual record/replay session editor with a multi-provider AI assistant (Claude, Gemini, OpenRouter) — drive it from n8n, Claude Code, or standalone.
🚀 Zero-backend, 100% client-side local AI assistant starter template. Powered by WebGPU and Google LiteRT-LM (Gemma 4). Offline-first PWA with multi-language TTS, customizable personas, and GitHub Pages deployment in 5 minutes.
A privacy-first PDF processing engine that runs entirely in your browser—deconstructing documents into text, images, and tables, then reconstructing them into pristine, structured Markdown. Static React SPA with client-side AI vision via Ollama, OpenRouter, or Gemini. Your files never leave your machine.