
I'd start a long agent run, walk away, and come back to find it had spent 20 minutes waiting on me to approve one file edit. Port22 puts every coding agent running on your Mac onto your phone. See which are working and which are stuck. When one needs permission your phone buzzes and you tap the actual option it offered, not a guessed keystroke. It attaches to what you already run. No wrapper, no config, no new terminal. Free for one Mac and two sessions, every feature on.
Loading comments…
Achievement
Project Info
Product Keywords
Port22 is a companion app that puts your coding agents on your phone. It connects to Claude Code, Codex, or OpenCode sessions already running in your Mac's terminal and mirrors them live to your iPhone. You read the transcript as the agent works, get a push notification when it needs you, and approve actions with a tap — no wrapper, no new terminal, no configuration. It's currently in beta and free for one Mac with two sessions, with every feature included.
Every token the agent thinks, edits, and runs is streamed straight to your phone. You're not waiting for a summary — you're reading the actual session as it happens, in real time.
When the agent finishes or needs permission, a push lands on your phone. Open it and tap the exact option the agent offered — not a guessed keystroke — and the session continues without you being chained to the desk.
A live count sits in the Dynamic Island, and the full roster of active sessions appears on your lock screen. You never need to open the app to know where things stand.
On your home network, Port22 connects over LAN. Away from home, an end-to-end-encrypted relay forwards the session over cellular — the relay never holds the keys and can't read your code. Pairing rides your iCloud account, so there's no separate login.
Port22 attaches to what you already run — it drives the session you started, not a fork of it.
That's the core difference. Most agent tools want you to adopt a new workflow or a new terminal. Port22 simply watches the sessions you already have open in Ghostty, kitty, Alacritty, WezTerm, tmux, or Terminal.app, and mirrors them to your phone. It's a zero-config attachment, not a replacement. The iCloud pairing is equally frictionless — sign into the same Apple ID on both devices and they find each other, no QR codes or new accounts.
You're already running Claude Code, Codex, or OpenCode on a Mac and you've ever felt trapped by an agent that stalls waiting for your approval. If you want to step away from the desk without losing visibility or control, Port22 is worth a spot on your waitlist. It's free through the beta, so there's no cost to trying it when it lands.
Other tools you might consider
You're running more coding agents than ever, but you can't keep up with them. That's where AgentPeek comes in. It pulls every session up into your Mac notch, live. Glance up, approve a prompt, watch token usage and manage the entire flow without pausing your YouTube video. All local, all yours.
The Termi Protocol is a 3D simulation of AI agent workflows. Give your coding agents a face, a desk and a living room. Watch them read, write and run commands live in 3D, like a game. You run the agents; we visualize the process.
GitHits gives coding agents access to the open-source code your app depends on. Get real implementation examples, dependency source navigation, package inspection and documentation. Agents can grep and read your codebase. They can't grep and read the open-source code your app depends on. That's where they start guessing, retrying, and looping. GitHits builds a version-aware index on demand. Agents can search, navigate, and inspect the code behind their dependencies. CLI: npx githits@latest init
Most agents pass their evals and fail in production. Prefactor is the evaluation layer that closes the gap. We score every agent run in real time, surface quality regressions and drift as they happen, and show engineering teams exactly how their agents are performing at scale. Built for the teams shipping agents to customers.
Maker
blueprint_b
Compare with
Alternatives
Loading comments…