TermIQ — Your Terminals in Your Pocket

Kick off a Claude Code task in VS Code, walk away, and approve its next step from your phone — without coming back to your desk.

TermIQ syncs the terminals running in your VS Code editor to your phone in real time. Run Claude Code, Gemini CLI, Cursor, or any terminal as usual — TermIQ pings you the moment a task finishes, pauses for a Y/n, or an AI agent fails, and lets you respond on the spot from termiq.io. Your machine does the work. Your phone keeps you in control.

Also runs headless: the @termiq/cli agent (npm i -g @termiq/cli) brings the same remote control to SSH boxes, CI runners, and any plain shell.

Why TermIQ?

What you get

Stay in the loop without staying at your desk

• Push the moment it matters — get notified when a terminal completes a task, waits for a Y/n confirmation, or an AI agent in it fails, even with your phone in your pocket.
• Answer from the notification — approve or decline an AI assistant's next step in one tap, without opening the app.
• Quiet Hours — silence overnight pushes so you stay in control without burning out.

Built so you can trust it with your terminal

• End-to-end encrypted — terminal content is encrypted on your devices with XSalsa20-Poly1305. The TermIQ server is a blind relay: it passes encrypted data and cannot read it.
• Streamed, never stored — your output flows through and is gone; nothing is persisted server-side.

Reliable enough for real work

• Reliable input — what you type from the train reaches the terminal in order, even when the signal drops.
• Sub-second sync that reconnects on its own — live output mirrors to your phone with sub-second latency and recovers automatically when your network changes.
• Follow the files your agent touches — see which files your terminal activity changes as it works, so you can keep up without opening your editor. On by default, respects your .gitignore.

Works with Claude Code, Gemini CLI, Cursor, and any other terminal — TermIQ mirrors whatever runs in the terminal, so there's nothing AI-specific to configure.

Screenshots

Dashboard — All Your Terminals at a Glance

Mobile — Monitor and Respond From Anywhere

30-Second Setup

1. Install the extension
2. Ctrl+Shift+P → "TermIQ: Login"
3. Scan the QR or paste the code in your browser to authorize
4. Open termiq.io on your phone and add it to your home screen
5. Run "TermIQ: New Terminal" — it's now in your pocket

Only terminals created with TermIQ: New Terminal are synced — pre-existing VS Code terminals aren't captured.

Commands

All commands are prefixed with TermIQ:.

Settings

Configure in Settings (search "TermIQ") or in settings.json.

Notifications and privacy

A notification tells you that a terminal is waiting, not what it asked. The question and its buttons travel to your phone encrypted and are readable only by your own devices — the server relays ciphertext and cannot open it.

Notifications never carry the question, whatever the settings: the server puts no terminal text into them. termiq.pushPromptText, which used to put the question in the notification body, no longer has any effect, and you can remove it from your settings.

When an agent fails

You get a notification when an AI agent (Claude Code, Codex, Gemini CLI, Copilot, Cursor Agent, Aider and others) in a TermIQ terminal exits with an error, and when the terminal's shell is killed, by the out-of-memory killer for example. Stopping an agent with Ctrl+C, a clean exit, a failing command that is not an agent (a build, grep, git), the shell staying open after the agent, closing the terminal and closing VS Code are not failures. The notification says only that the task failed, never the error. One failure gives one notification, and a terminal gives at most one a minute.

Only the shell knows how a command inside it ended, so TermIQ terminals start bash and zsh with a small hook that reports the exit code and the program name of each command to the extension, in a sequence the terminal ignores. Each hook signs its reports with a random value only its shell knows, so text that merely passes through the terminal, a file you cat or the output of a remote host, cannot fake a failed agent. The hook only adds itself: your ~/.bashrc or .zshrc load as usual and are never changed, and its file lives in a private temporary directory while the shell runs. Other shells, and every shell on Windows, start as before; there a failed agent is noticed only if your own shell integration reports command ends (OSC 133). Turn the hook off with termiq.shellIntegration (for terminals you open afterwards).

How It Works

VS Code ──▶ TermIQ Server (blind relay) ──▶ Your Phone
   │              cannot read content              │
   └────────── End-to-end encrypted ───────────────┘

Your terminal data is streamed, not stored, and end-to-end encrypted — only your devices can read it.

Requirements

• VS Code 1.109 or newer
• A free TermIQ account at termiq.io
• iPhone push requires iOS 16.4+ (Android supported too)

Plan

Free forever — 1 agent and 2 terminals, no credit card required. Upgrade any time for more.

Links

• termiq.io
• Documentation
• Report an issue

Free forever for personal use. Start now at termiq.io