I'm Pete Stergion, a higher education technology leader with 20 years driving technology adoption across complex academic institutions. Today I lead AI adoption at Cornell University as a Tech Lead on the AI Innovation Hub, helping departments put Claude-based workflows into research, teaching, and operations.
This site is how I actually work. Claude Code is my office suite: where I write code, manage servers, deploy websites, run security audits, and publish this. Not through chat conversations, but through a system of specialized agents, custom MCP servers, and self-hosted infrastructure that all connect through one terminal.
Everything here is real, running in production, and used daily. I spent twenty years with a head full of automations I could see but couldn't build. Claude removed that barrier: since then I've shipped MCP servers, a 15-agent system, and production tools I never could have built alone. The only limit left is the idea itself.
Rebuilt my workspace machine on NixOS today. Wanted native Linux instead of juggling WSL or fighting macOS quirks, and I wanted the whole setup to live in one file instead of a pile of installs I'd forget how I made.
That file is the actual system. Every package, every service, every shell shortcut...
Strava MCP server with SQLite caching, automatic token refresh, and rate limit awareness. Built with FastMCP.
Python / FastMCP / Docker / SQLite
Labeled-row status bar for the Claude Code TUI. Context usage, billing tier, git status, weather, and session metrics.
Shell / Claude Code
A Claude Code skill that produces citation-grounded research reports with strict anti-hallucination rules.
Claude Code / Markdown
SearXNG MCP server for Claude Code. Web search, news, deep multi-page search, and people lookup via self-hosted SearXNG.
Python / FastMCP / Docker
Threat intelligence MCP server for Claude Code. IOC lookups, CVE checks, breach monitoring, dark web search, and OTX pulses.
Python / FastMCP / Docker