From the Sunset District, San Francisco
I’m Tony, an SRE in San Francisco. Nights and weekends, I build software with a focus on privacy.
See what I’m building01 / About
I live in the Sunset District with my family and two Shiba Inus who have perfected the art of treating every request as a suggestion.
I’m training for an ultramarathon. Most of my project ideas come from long runs, where I also think through how I might build them with AI. Nights and weekends are when I work on them.
I build from the same starting point: local-first, minimal dependencies, no tracking.
A native Bitwarden and Vaultwarden client for iOS, iPadOS, and macOS. No third-party code in the runtime.
I reimplemented the crypto in Swift and check it against RFC vectors and weekly differential tests with the upstream C reference. Vault data stays ciphertext at rest. On macOS, an ssh-agent signs git operations behind Touch ID.
A browser engine built from scratch in Rust, with 23 crates covering HTML parsing, layout, and GPU rendering.
A screenshot-reference test corpus and per-subsystem maturity docs say where compatibility ends. I’d rather publish the honest maturity table than the demo. The repository is private for now; I’m happy to walk through it.
An MCP server that gives AI models scoped access to Kubernetes clusters. Secrets are redacted by default, and destructive operations require human confirmation.
KUBECONFIG never leaves the local process. The project is still in progress.
Presence-first messaging for small, trusted networks. Inspired by ICQ, with a buddy list and numeric UINs.
Accounts are invite-only and never ask for a phone number or your address book. Use the hosted version, or self-host it in about fifteen minutes. The project is still in progress.
03 / Process
Alongside the software, I’m working on how I build it. Each project gives me a chance to improve the workflow: how I write specs, divide up the work, and check what the models produce.
I’ve tried development agents paired with QA agents, models interviewing other models, and agents testing across platforms. Those experiments inform the next project. I’m getting more deliberate about what to delegate, what needs an automated check, and where I need to stay involved myself.
Sometimes a lesson sends me back to an earlier project. More than once, I’ve restarted one because something I learned elsewhere changed how I wanted to build it. That’s becoming part of the process, too.
04 / Contact
If you want to talk about a project or compare notes on building with AI, email me.