Sandbox Relay vs AgentOS

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.

AgentOS runs your coding agents on your own computer. This app is how you keep up with them when you're away from it. See every session at a glance. Sessions are grouped the way the web app groups them: pinned, needs you, working and done, with live status as agents start, finish or stop to ask something. Answer what's waiting on you. When an agent asks a question or needs approval to run a command, it shows up under Needs you. Reply, decline, or open the conversation to see the context first. Keep the conversation going. Read replies as they stream, with code highlighted, diffs with line numbers, diagrams and tables. Send a message, queue the next one while the agent works, stop a turn, or send a queued message right away. Attach photos from your library, camera or Files. Pick the model, how much the agent may do without asking, and plan mode, from the same composer as the web app, with the agent's slash commands and @file search. Your machine, your data. The app talks only to the AgentOS you run. Add it by its address on your network or tailnet, or through AgentOS Connect, and pair it with a one-time code. Nothing passes through a server of ours, and the app collects no data. Requires AgentOS running on a Mac or Linux machine you can reach.