CodeMote - Claude Code, Codex, any CLI agent. Driven from your iPhone
by•
CodeMote pairs your iPhone to your machine or VPS and gives you the real sessions. Live terminal on your lock screen, push when your agent needs approval, full diffs, complete git flow. Direct encrypted connection. Your code never touches our servers.
Replies
Driving CLI agents from a phone makes sense if the workflow is approval-first, not blind autonomy. The best version of this is probably checkpoints, logs, and one-tap continue/stop decisions while the heavy work stays on the Mac.
CodeMote
@krekeltronics Exactly our thesis. CodeMote isn't remote-desktop-for-agents.. the heavy work stays on your Mac, the phone is just a controller.
That means:
Checkpoints, not blind autonomy: you see the agent's state (running / waiting on you) and approve permission prompts from your phone.
One-tap continue/stop: Live Activities + push tell you the moment an agent is waiting, so you decide from the lock screen instead of checking every time the app.
Logs you can actually read : live terminal streaming + scrollback, so a decision is always backed by context, not a guess.
Approval-first is the whole point. The Mac does the work; CodeMote let's you control it from your phone
the lock-screen 'flips to waiting + push' is the real product. hard part is knowing when NOT to ping. does it batch approvals, or one buzz per stop?
CodeMote
@andrewzakonov Batches per-terminal: one buzz when a terminal goes idle/needs approval, not per stop, and it's suppressed entirely while you're in the app, so you only get pinged for sessions you're not already watching.
Dial
the "start claude code, wait 20 minutes, answer one question" loop is real, i lose so much time just standing near my desk in case it needs an approval. no relay server touching the code is the right call, that's the one thing that would've made me not even try it. genuinely curious about approving a plan from the lock screen though, do you get enough of the diff to actually judge it or is it more of a glance and trust situation when you're not at a full screen
CodeMote
@omri_ben_shoham1 hey Omri! thanks for the question.
Right now you can't approve from the lock screen, right now the lock screen activity is only a streaming of what the agent does, to actually approve, clicking the activity, you'll go in the agents and have a full picture of what it has done. and once you are in the app, you have full access to all the file changes, everything your agents has done so far.
this is the exact flow you would do on your laptop
Dial
makes sense, that's actually the safer default. glancing at a lock screen notification and blind-approving would be worse than being forced to open the app and see the real diff. good to know the two are intentionally separated
solid product when you are addicted to code and don't want to take your laptop with you
CodeMote
@eliana_jordan Hey Eliana, really appreciate your comment!
and yes I built codemote for the devs like me that want to bring everything on a walk :)
Keeping the code on your own machine is the part that matters. Remote coding from a phone sounds much safer when it works like a control layer for your existing workstation, not another place where the repo gets copied.
CodeMote
@farrukh_butt1 Exacly, codemote is just the controller, not the brain, everything stay safe inside your laptop/server, you just extend the way you are using it
The "start agent, wait 20 minutes, answer one question" loop is exactly my day building a SaaS solo. One thing I'd want: when the agent asks something that needs actual code reading to answer well, do you find the phone diff view is enough, or do those decisions still wait for the desk?
CodeMote
@kojimajunya hey thanks for the question! nowdays i’m used to review diff on my phone, but for a new user can be tricky, but trust me you’ll get used too :)
Being away from my desk no longer meaning the work just stalls is a quietly freeing idea, and glancing at my phone to nudge things along from wherever I am sounds genuinely good, Salvatore.
CodeMote
@xavier_macia PRECISELY!
you just need your phone and in 99% of the case you're bringing it anyway, and you can do what are doing at home but anywhere
GPTEverywhere
Congrats on shipping this — the Live Activity + push when the agent blocks for approval is the part that actually makes mobile control usable for long Claude Code runs. Direct tunnel with no code on your servers is the right call for this crowd.
CodeMote
@ducan thanks, really appreciate your comment 🤞
The Lock Screen Live Activity feels like the real wedge here: most agent runs are not fully hands-off, they are long stretches of waiting with 1-2 tiny human approvals.
One thing I'd love to understand is how you separate a safe approval from a risky one on mobile. A compact diff summary plus the exact command/action being approved would make the phone workflow feel much safer than just mirroring the terminal.
CodeMote
@grace_lee26 hey, thanks for the comment!
the app itself is just an extend version of your laptop, so the flow to approve/review something is the exact same in both
you have access to all diff files, all things your agent said in the chat
Using a phone as the control surface for CLI agents is a fun angle. I’d want a very clear pause/approve step though — remote agent runs can get messy fast when they touch files.
CodeMote
@xiaosong001 what do you mean by clear pause/approve steps?
right now is the exact flow you would have in your laptop, identical