$ loading…
Things I build off the clock — agentic AI tooling, MCP servers, and the self-hosted infrastructure they run on. Each one exists to answer a specific question: can agents share a box without leaking state? can email be an MCP tool? can a prompt improve itself without a human in the loop?
A Model Context Protocol server that gives AI agents first-class email — read and send over IMAP/SMTP, behind Proton Mail Bridge so the agent never touches raw credentials.
Two isolated instances of an open-source agentic AI system on one home server — three Docker Compose stacks (shared Caddy + one per instance) with separate credentials, volumes, and networks.
Slash commands that make agentic-coding sessions faster and more reliable — a silent health check, an iterative prompt loop backed by state files, and an eval-gated prompt improver.