Murmur BLE Shell vs Sandbox Relay

murmur turns your phone into a remote control for a Raspberry Pi — no Wi-Fi, no network setup, no port forwarding. Just Bluetooth Low Energy (BLE), directly between your phone and the Pi. HOW IT WORKS Install the open-source murmur daemon on any Raspberry Pi running Linux, pair your phone with it over Bluetooth, and you get: • Shell mode — a real interactive terminal on the Pi, right from your phone. • Agent mode — describe what you want in plain English ("what's eating my disk space?", "set up a static IP") and an AI agent plans and runs the shell commands for you, showing every command and its output as it goes. BRING YOUR OWN API KEY Agent mode is powered by your own Anthropic Claude, OpenAI, or Google Gemini API key — entered once in Settings, stored only in your phone's secure keychain. murmur has no backend server and no account system. The only network calls it makes are the LLM requests you trigger yourself, using your own key. WORKS OFFLINE ON THE PI SIDE The Raspberry Pi never needs an internet connection. It just needs Bluetooth and the murmur daemon running. Good for headless boxes, home labs, and devices you'd rather not put on a network at all. PRIVACY BY DESIGN Everything murmur stores — the Bluetooth pairing key, your API key, an optional per-device sudo password, and saved agent conversations — stays on your phone in the OS-level secure store. One tap in Settings wipes it all. OPEN SOURCE Both the daemon and the app are open source: github.com/nekonihq/murmur

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.