PERSONAL PROJECTS

A Wayback Machine archiver that keeps retrying while the Internet Archive is busy, until your pages are actually preserved.

Finds people from underrepresented groups missing from English Wikipedia and fact-checks every claim into a research dossier. A human writes the article itself.

A local-first, read-only engine that turns order emails into a structured catalog of what you own, what's coming, and what you spent.

Unofficial API for MyFigureCollection.net, written after eight years of an officially promised API v4 that never shipped. A Python library plus a local MCP server with 12 tools, covering item search, JAN barcode lookup, partner shop prices, collections, and clubs.

17-agent AI system for personal life management, built in Craft on Claude MCP. Each agent owns one life domain: triage, career, finance, events.

Background intelligence sweeps for two domains: Japanese reading practice from live news, and structured job-opportunity cards. Results land straight in Craft via MCP.

No public repository.

Native macOS port of gitChara-dot's Yaha-Pet: Usagi, Hachiware, and Chiikawa roam the desktop. Two bug fixes offered back upstream in an open PR.

Native macOS port of CookieElmo's wellness-reminder pet from itch.io, rebuilt on the official Godot runtime. It reminds you to drink water.

Natural-language query system over 60,000+ anime titles: PostgreSQL, a local ReAct SQL agent, and a Streamlit frontend. CMU capstone, presented at Anime Boston 2026.

ETL pipeline that turns Twitter/X export files into a searchable dataset with NLP sentiment and topic classification, built for longitudinal self-analysis.

Interactive case study mining a decade of personal social media data (26,720 Twitter likes, 4,500 saved YouTube videos, 500+ LinkedIn connections) to reveal what the algorithm sees. CMU data mining final project, published as a scrollytelling site.

Book recommender that fine-tunes LoRA adapters on Llama 3 8B to score books on story attributes, starting with genre read from the plot summary alone (16,000+ Wikipedia summaries). CMU machine learning group project with Justin George and Mika Ishida.

Coursework; no public repository.

Tableau study of light novel publishing in Japan and the US from 1975 to 2024: the rise of isekai, which titles get anime adaptations, and whether an anime makes an English translation more likely. CMU data visualization final with Mika Ishida.

Coursework; no public repository.

Evidence-based music tagger for macOS that cross-examines three independent witnesses (Shazam, AcoustID + MusicBrainz, iTunes) into six scored signals and a verdict tier per file. Treats a cover as a first-class verdict instead of a wrong catalog match, and never writes a tag it can't prove.

Automated open-data release calendar for licensed English manga, manhwa, manhua, and webtoons, forked from LNRelease's engine with a rebuilt VIZ scraper and historical calendar backfill. Daily and weekly GitHub Actions scrape 15+ publishers, auto-commit, and auto-deploy the site with no human in the loop.

Media-collection sync engine keeping 1,600+ records aligned between a REST API and cloud storage, using GPT-4o fuzzy matching with a human-in-the-loop review UI.

In progress; no public repository.

GitHub keeps only 14 days of repository traffic history, so a private pipeline snapshots every repo daily into permanent CSVs with a self-updating README dashboard.

No public repository.

Recommendation quiz that matches readers, viewers, and listeners to the right Odyssey adaptation. 24 static pages covering 17 versions (translations, film, novels, albums, games) with structured data and FAQ content built for search and AI answers.

Hub for a family of adaptation guides built on one recommender engine and one catalog model. Every story gets its own property, quiz, and comparison matrix, with structured data and FAQ content built for search and AI answers.

Citation-first RAG Discord bot for Uma Musume game mechanics, answering with page-level source attribution from a 200+ page community reference doc.

Desktop GUI that turns K-pop idol photos into convention-ready 1.5" button designs: automatic face detection, production-spec cropping, bleed margins.

No public repository.

An agent-maintained catalog of free student and alumni perks: searchable list, campus map, weekly link checker. Live for Dartmouth and CMU; forkable for any school.

Substack newsletter on AI tools and data systems for practitioners: the intersection of technical work with everyday life.

Dartmouth senior thesis running experiments on GPT-3 months before ChatGPT's release, analyzing mobile-gaming monetization and player behavior.

No public copy.

Ethics review of a car-insurance pricing model across data ownership, explainability, fairness, bias, safety, and liability. Compared SHAP feature importance with DiCE counterfactuals and red-teamed a customer-service chatbot. CMU Ethics and AI group project with Justin George and Mika Ishida.

Coursework; no public repository.

React SPA for tracking apartment decluttering zone-by-zone: 15 zones, sprint mode, deadline countdown. Built for real use before a trip.

Notch-native dictation for macOS, and a hard fork of OpenSuperWhisper. Tap Fn and Control, speak, tap again, and the transcription lands in whatever field was already focused. The upstream project owns the engine; this fork reshapes the trigger and the interface.