CodeMote

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.

The Lock Screen Live Activity flipping to waiting with a push is what actually makes this desk-free, since long agent runs are mostly idle waiting for one approval. When I have two or three agents going at once (say Claude Code and Codex in separate sessions), do they each get their own Live Activity/terminal, or is it one merged stream where I have to work out which agent is asking? And if the tunnel drops mid-run, does the session survive on the machine side and re-attach, or is the terminal state lost?

this is the thing I actually want, I keep starting a session then getting pulled away before it needs the next approval. one thing I'd be careful about is approving a big diff from a 6 inch screen while distracted, it's easy to skim and tap approve on something you'd catch immediately on a real monitor. do you have any friction built in for large or risky-looking diffs, like forcing a scroll through the whole thing before the approve button unlocks, versus treating every approval the same regardless of size

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?

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.

solid product when you are addicted to code and don't want to take your laptop with you

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

I enjoy that it works with different CLI agents instead of locking people into one option. Could shared sessions allow another teammate to approve requests when I am unavailable because that would help distributed teams?

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?

how does the encrypted connection actually hold up on sketchy hotel wifi, and is there any fallback if the direct pairing drops mid-session?

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.

I think speech to text fits this workflow well. Could custom voice shortcuts approve common actions even faster?

Does CodeMote support juggling multiple agent sessions at once, like Claude Code on one project and Codex on another, from the same phone view?

Me using my phone for approvals sounds practical instead of carrying laptop everywhere. Would offline notification retries help when the connection drops for a few minutes?

The lock screen terminal integration is genuinely clever, feels like something Apple should have shipped themselves. Love that the connection stays direct and encrypted too, the no-middleman approach is the right call for dev tools like this.

Finally tried it on my VPS and the lock screen terminal blew me away, actually usable for quick checks. The encrypted direct connection is a nice touch too.

The interesting constraint here isn't the iOS interface, it's latency and interruption. CLI agents mid-task don't always pause cleanly, and if you're driving one from your phone on a spotty connection and the session drops, you need to know whether the agent kept going, stopped, or did something half-finished that left the repo in a weird state. Curious how CodeMote handles that. Also wondering whether you have any visibility into agent output in real time or if it's more of a fire-and-check-back situation, because the value of mobile control drops a lot if you can't actually watch what's happening.

Hi PH!
I built CodeMote because my workflow became "start Claude Code, wait 20 minutes, answer one question, wait again." I was stuck to my desk waiting an agent that needs me only few times.
CodeMote pairs your iPhone or iPad directly to your machine. And is not only a terminal inside a phone, is a full workspace (git, file editor, speech-to-text, servers)
And the part I'm most proud of: the terminal streams live into a Lock Screen Live Activity. When your agent stops to ask something, it flips to waiting and sends a push. I have approved plans from the beach, the gym, without bringing my pc with me.
My record is a full feature shipped from a motorcycle stop.
Technical bits, because this crowd will ask:
• Agent agnostic. If it runs in your terminal, it runs in CodeMote. Claude Code, Codex CLI, Gemini CLI, opencode, aider, whatever comes next.
• Works via a VS Code/Cursor extension, or npx codemote-cli on any machine, including a headless VPS.
• Connection is a direct encrypted tunnel, devtunnel by default, Tailscale or ngrok, adding cloudflare too, if you prefer. There is no relay server. My servers never see your code or your session. That was non-negotiable for me.
I'll be here all day. Tell me what's missing, what's broken, and what you'd need to actually leave your desk while your agent works.