Current public GitHub stars across Wolfie’s repositories. Refreshing live count.
A benchmark that scores web-search providers (Exa, Perplexity, Tavily, Gemini, Grok) on everyday research quality and — the differentiator — landscape recall: whether a search surfaces every real competitor in a market, including the obscure long-tail that naive agent fan-out misses.
Interactive time-lapse map of San Francisco metered parking activity, built from 206M+ meter transactions and shared through a viral X demo.
A time-warp animation of one week of San Francisco traffic: every bridge, artery, and neighborhood pulsing through seven days of real movement data.
An interactive model of GPU compute economics: what a token actually costs across hardware generations, utilization rates, and hosting strategies.
Live AI model landscape dashboard tracking model quality, pricing, speed, benchmark trust, and leaderboard movement across providers.
Turns 94k+ benchmark results and 17k+ price points into a browsable model intelligence dashboard.
Historical context for today's weather: live San Francisco conditions compared against 100+ years of NOAA records, microclimates, and climate trends.
Puts every forecast in century-scale context by fusing live Open-Meteo conditions with 100+ years of NOAA GHCN records.
Drive a real, logged-in Chrome profile from local scripts via a Native Messaging bridge. No remote-debugging popup, no separate browser profile.
AI-native platform for financial research providing LLM-ready SEC filing data with semantic search, RAG chat, and structured table extraction.
Turns SEC filings into LLM-ready context with citation guarantees, cutting research time for analysts by 70%.
Full-stack MMA fighter database with 76,000+ fighter profiles, 270,000+ fights, and real-time stats. A Pokedex-style experience for combat sports enthusiasts.
Indexed 270k+ fights with sub-150ms search so analysts can answer matchup questions in seconds.
MCP server enabling AI-assisted music production in Ableton Live. 50+ tools for MIDI manipulation, automation, groove control, and arrangement—all controllable through natural language.
Unlocks hands-free music production by wiring 50+ MCP tools directly into Ableton’s Live Object Model.
A searchable archive of court documents with OCR text extraction and full-text search capabilities. Makes publicly released legal documents accessible and navigable.
Makes publicly released legal documents searchable and accessible via OCR and full-text search.
32+ merged pull requests across the agent-tooling ecosystem: terminal rendering, performance work, and UX in the tools I use every day.
The agent development environment for running fleets of parallel coding agents. Contributions span terminal rendering, performance, and workspace UX.
AI coding agent for the terminal. Contributions across the coding-agent core, TUI, and provider layer: caching, mouse routing, and correctness fixes.
Multi-provider AI proxy. Contributed model registry metadata for new frontier models.
Pure-Rust spreadsheet library for reading and writing XLSX. Contributed upstream fixes discovered while building high-performance Excel tooling.
My journey started in finance — advising on IPOs and complex accounting at PwC CMAAS, where I led ASC 606 implementations and automated data pipelines for aerospace CFOs.
I kept running into the same problem: advisory teams spend half their engagement chasing documents, re-requesting data, and manually organizing client uploads. The workflow hasn’t changed in decades.
Now I build the software I wished existed back then - AI-native tools that bring structure and source-backed intelligence to document-heavy financial workflows: request-list movement, workbook evidence, cited answers, and deterministic tie-outs. I’m looking for an engineering team where finance depth plus AI-native product sense is an edge.
Send the thing you’re thinking through: product, finance workflow, agent tooling, or a messy system that needs structure.