122 days. 547 commits. 160,000 lines of Swift. One native macOS app.
About $322,000 of Claude at API rates went into building it. That is the API-rate valuation of measured usage rather than cash I wired anywhere, and I would rather say it that way than round it up.
Grux is a native macOS agent for people who work alone.
It opens real terminal sessions and can undo anything it did, because every command is snapshotted into a shadow git repo first. It runs swarms of agents in parallel, scaffolds and builds iOS apps, captures meetings on device, and writes its own next version for you to approve.
39 features, 79 tools, 1830 tests. Your own API key, or a local model with no key at all. No account, no server, no telemetry. MIT.
It doesn't even have to be a big dramatic failures, more the small moments where something clicked and you went from trusting the output by default to double checking everything. For me it was watching an agent confidently rename a function across twelve files, then leave the original function untouched in a thirteenth file it apparently didn't search, with zero indication anything had been missed. It wasn't even a hard case, the file just wasn't in the directory it happened to grep first. What was your moment? And did it actually change your workflow afterward, or did the trust creep back in after a week like it always seems to for me?
