AgentPort vs Sandbox Relay

Agent Port is a local-first monitor and remote control surface for the AI coding agents you already run — Claude Code, Codex, and other CLI agents living in tmux on your Mac. Check on them, steer them, and reply to prompts from your iPhone, anywhere on your own network. WHY AGENT PORT Long-running agents don't finish on your schedule. Agent Port keeps you in the loop without keeping you at your desk: see at a glance which sessions are running, which are waiting for your input, and which are done — then jump in and respond. WHAT YOU CAN DO • Live session list — every agent pane with a clear status: running, waiting for you, done, or idle • Real-time logs — stream a session's output as it happens, with copy and auto-follow • Full terminal — a real PTY bridge when you need to type anything, not just presets • Quick replies & keys — send text, common answers, and control keys with one tap • Token usage — total Claude Code and Codex token consumption, right at the top • Multiple machines — save server profiles and switch between your Macs instantly • Picture-in-Picture — keep a session's log floating while you do other things (iPhone) LOCAL-FIRST & PRIVATE There is no Agent Port cloud. The app talks directly to a small, free, open-source service you run on your own Mac, over your LAN, Tailscale, or any network you control. Your code, sessions, and tokens never pass through our servers — because there are none. The app collects no analytics and stores its settings only on your device. TRY IT INSTANTLY On first launch the app opens in Demo mode with fully populated sample data — no server, no account, nothing to configure. When you're ready for real use, run the open-source service on your Mac and switch profiles with one tap. Source code, setup guide, and documentation: github.com/xiaoxiunique/agent-port Requires a Mac running the free Agent Port service to monitor your own agent sessions.

For developers who run Claude Code or Codex in Docker Sandbox, Sandbox Relay is the phone client for driving that agent. It is a companion, not a standalone app: it needs a broker you run, with an agent connected behind it. Kick off a task from the train, check on a long-running job from the couch, or steer the agent while you are away from your desk. Docker Sandbox runs each agent in its own isolated micro VM. A small broker you self-host sits in the middle: you send work from your phone, the broker passes it to the agent, and the streamed reply comes back. Your infrastructure, your agent. The app is just the remote. New to this setup? The app's support page explains how it works and what you need to run it. WHAT YOU CAN DO - Connect to your broker with a URL and a bearer token. Connections use HTTPS, with plain HTTP allowed only for local-network addresses. - See every connected agent at a glance, with live online/offline status. - Send the agent work and watch its reply stream in token by token. Stop a turn mid-stream, or start a fresh thread whenever you want. - When an agent goes offline, its thread stays readable as history. - See per-turn input and output token counts when the broker reports them. - Save reusable prompts as local notes, organised by hierarchical tags like #work/project/feature. Drill down by tag, copy a note straight into a thread, or link a note to the thread it came from. Notes live on your device only; they never touch the broker. WHAT YOU NEED - A broker you run, reachable from your phone (over your local network, or remotely through a tunnel or private network you control). - A coding agent, Claude Code or Codex, running in Docker Sandbox and connected to that broker. PRIVACY Sandbox Relay talks only to the broker you configure. Your access token is stored securely on your device and sent only to that broker, to authenticate you; it never goes to the developer or any third party. Your notes stay on your device and are never sent anywhere. No third-party analytics, no account to create. Note that the app streams whatever your agent outputs, verbatim.