Great to see. It’ll be great to democratize access to remotely using cli coding agents.
I’ve been iterating the past few months on a solution to use Claude Code on my phone while it runs on my laptop and it’s a lot of moving parts: Tailscale, git worktrees, tmux, an always-on “caffeinate” process, and a ton of hooks & tweaks to fix bugs along the way. It’s become very comfortable but in the process, impossible for anyone but me to understand.
But it’s awesome because I own the machine that runs tests and am not paying monthly for anything but Claude Max - and it keeps going if I lock my phone or go into a cell reception dead zone.
Productising such a thing would be a very interesting challenge indeed.
Totally relate to the "tons of hooks & tweaks" part. I've been using Claude Code daily to build a macOS app solo, and ended up in the same rabbit hole — hooks, FSEvents, process monitoring, all duct-taped together.
The remote/phone side I haven't solved (your Tailscale+tmux setup sounds solid for that), but the "at my desk" problem — losing track of which terminal is doing what — I ended up productizing into a small menubar app called GroAsk (groask.com). It does two things: ⌥Space to quick-launch any AI, and a dashboard showing real-time status of all Claude Code sessions so you can jump to the right terminal instantly.
Very different scope from Omnara — purely local, purely desktop, no remote/phone stuff. But for the "I have 3 sessions running and forgot which one needs me" problem it's been a huge quality of life improvement for my own workflow.
Nice. For the “which session needs me” challenge I arrange windows spatially and use numbers for my worktree naming.
So the main repo is always the left-most, then worktree 1, and so on.
Rereading the Claude Code transcript is an excellent tool for getting back into the context of what I’m working on in a particular window.
I struggle to run more than 3 truly complex implementations at once, but can handle as many as 6 or 7 if I’m just fixing little bugs.