Diachron
Provenance for AI-written code: prompt → patch → verification → merge. “Git for agent actions”.
AI-native financial data platform.
An engagement workspace for document-heavy financial workflows. Request list management, intelligent document classification, and auto-ingestion - built to replace the email-and-spreadsheet chaos advisory teams live in today.
Provenance for AI-written code: prompt → patch → verification → merge. “Git for agent actions”.

Daemon-based architecture for AI agent tools. 19x faster than MCP stdio with sub-10ms latency via persistent UNIX socket daemons.

The fastest iMessage integration for Claude Code. CLI + daemon design avoids MCP overhead for "instant" UX.
A shareable inventory + analytics layer for your Claude Code setup, with an interactive TUI dashboard.
A personal operating system: projects, tasks, notes, and integrations—driven through an agent-first CLI.
AI-native platform for financial research providing LLM-ready SEC filing data with semantic search, RAG chat, and structured table extraction.
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.
Historical weather context for any location. Compare today's conditions against 100+ years of NOAA climate data with interactive visualizations.
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.
Turn raw LLM chat exports into structured datasets and research-friendly artifacts.
A searchable archive of court documents with OCR text extraction and full-text search capabilities. Makes publicly released legal documents accessible and navigable.

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.
So I’m building SynthGL - an engagement workspace that brings structure to document-heavy financial workflows. Request list management, intelligent document classification, version control, and auto-ingestion of financial data. The V1 wedge targets QoE and FDD teams, with architecture that extends to any recurring financial engagement type.
Have a project in mind or just want to say hi? I'm always open to discussing new opportunities and ideas.