Some of the stuff I've built or am currently building.
Browser automation toolkit - Chrome extension + CLI for AI agents (Cursor, Claude Code, etc) to control authenticated web apps via CDP
macOS desktop app for local, private STT voice transcription. Hold Option + Z and just speak. Powered by OpenAI Whisper and Nvidia Parakeet models.
AI character chatbot platform with persistent memory and context. Live on iOS App Store and Google Play.
AI agent that can SEE 👁️, control, navigate, and do stuff for you on your browser
One app every day challenge - exploring vibe coding platforms and shipping daily. Template generator for others to join.
Powerful multi-search CLI combining ripgrep, fd, dust, and fzf for blazing fast file discovery and analysis.
npm i -g @vd7/eyecli
Protect any macOS app behind Touch ID.
brew install vdutts7/tap/applock
Monocular Depth Estimation with a Single Image (MiDaS) using PyTorch and Open3D
Talking Head of your favorite rapper using Transformers (NLP), PyTorch, Tortoise TTS, and OpenCV
AI-powered mock interviews using DeepSpeech, spaCy, and OpenCV
Chat with your favorite YouTuber/channel on hundreds of videos using vector embeddings, semantic search, and GPT
Generate 1000+ piece NFT collections using AI and Smart Contracts
Browser game: an NPC bot roaming a plot
Automate TikTok views, likes, and follows