I shipAI productsend to end.

Cloud-based collaborative editor for Markdown writers with a custom GitHub-to-Convex sync engine, scheduled publishing via durable workflows, and multi-provider AI writing assistance.

A native SwiftUI menu-bar and dashboard app for Apple Silicon Macs that reads chip temperature, fan speed, and battery health straight from the hardware, presented in a UI that looks like Apple built it. Free and open source.

A native SwiftUI macOS app that automatically cuts long pauses and filler words (um, uh, hmm) from screen recordings — audio and video together — producing tight jump-cuts. Runs 100% locally, never touches the original, and includes experimental on-device ML models for filler detection.

A native macOS menu-bar app that watches the Downloads folder and quietly files each finished download into the matching folder on a NAS. Built to sidestep the macOS limitations that make a launchd cron job silently fail: SMB write scoping, throttled watchers, and TCC blocks.

A personal, for-fun macOS fork of VoiceInk — local, on-device speech-to-text dictation powered by whisper.cpp, with its own identity, GitHub-Releases updater, and stable/nightly/dev channels. A hobby project built to learn, credited fully to upstream.

A zero-dependency CLI that runs multiple Convex accounts across multiple projects at once — link a folder to an account once, and the right account activates automatically the moment you cd in. No logins, no deploy keys, no secrets in your repos.

Lovable moved 850K lines off Next.js with one developer and a pack of agents. The dev server numbers hurt to read on my 16 GB machine. I read the post five times and I am still staying on Next.js. Here is why both of us can be right.

Ten dollars buys twenty dollars of credit on Trae. I spent eighteen of it in one night, then found out Auto mode was routing to GPT-5.2 and Gemini Flash the whole time — and still shipped the work.

Copilot started with per-message pricing. Cursor promised unlimited. Now everything is token-based credits and rolling session windows. Here's how we got here — and why your subscription works the way it does.

Everyone's arguing about which model tops the benchmarks. Nobody's talking about the thing that actually decides whether your agent works — the harness wrapped around it. Here's what's inside one, why it matters more than the model, and why you're already building them without knowing it.

Rewriting big software used to be unthinkable. Then AI made porting a codebase a weekend job — and the thing every one of those ports leaned on wasn't the model. It was the test suite. Code got cheap. Tests didn't.