Fleet Command vs Sandbox Relay

Fleet Command is mission control for your AI coding agents. If you run Claude Code or Codex — on one machine or a dozen — it turns every live session into a ship on a space map you can watch, command, and answer from your phone and Apple Watch. Each ship is one coding session. At a glance you see who's thinking, who's running a command, who's waiting on you, and who's gone quiet — across all of your computers at once. THE MUSTER — your home base. One ranked list of everything that needs you, across every machine. Approve a blocked command, answer a question, or jump to a session, and clear it to zero. FLEET ATLAS — a living map of all your machines at once. Each computer gets its own territory, sized to fill your screen, with its sessions drifting inside it: green when it's humming, amber when a session is awaiting a command, red when something's blocked. Reorder your fleets with a drag, and tap one to dive in. FLEET INSIGHTS — a dashboard for your whole fleet. See what your agents spend their time on, how fast they're burning tokens, when you're busiest, and which tools, sub-agents, and skills your sessions use — across every machine, per machine, or all at once. ANSWER FROM ANYWHERE — approve or deny a risky shell command, or type a reply straight into a live session, right from the notification on your lock screen or your Apple Watch — without even opening the app. Dictate a reply from your wrist. Approve a tool once, or for the whole session. NOTIFICATIONS THAT RESPECT YOU — mute a noisy fleet, choose which alerts actually buzz you, and let quiet digests roll up the rest, so you're paged for the one that matters and never flooded. NEVER MISS THE ONE THAT MATTERS — distress timers show how long a session has been blocked and escalate as it waits. A fan-out of identical requests collapses into a single tap. Search across every machine to find any session fast. ON YOUR WRIST — a watch-face complication and Smart Stack glance show who needs you without opening anything. Approve, deny, or reply right from the watch. A Lock Screen Live Activity and Dynamic Island surface "a ship needs you." KNOWS WHEN A MACHINE GOES DARK — if a computer sleeps or drops offline, its sessions are marked offline instead of falsely flagged as stuck, so you're only paged for things that are really waiting. MULTI-MACHINE — Mac, Linux, or Windows, wherever Claude Code or Codex runs. Watch them all from one place. PRIVATE BY DESIGN — Fleet Command never sees your source code, your prompts, or your full file paths — only lightweight session metadata and a project folder name. Insights are derived on our side from that same metadata, so nothing extra runs on your machine. No accounts, no email, no password: pair a computer with a one-time code. HOW IT WORKS — install the open-source companion plugin on your computer, link it with a pairing code, and your sessions stream in live. Tap "Preview a demo fleet" to try the whole experience instantly, with no setup. Fleet Command is an independent developer tool. It is not affiliated with, endorsed by, or sponsored by Anthropic or OpenAI. "Claude" and "Claude Code" are trademarks of Anthropic, PBC; "Codex" is a trademark of OpenAI.

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.