Credentials. Remote approvals from a phone can start actions on your Mac, so only approve requests you recognize and keep Face ID enabled.
Who it is forA developer who starts long agent runs on a Mac and leaves the desk while they work.
The problemAgents stall on permission prompts while the developer is away, and there is no way to see or approve them from a phone.
The outcomeThe Mac session moves to the iPhone Lock Screen and Dynamic Island, and each permission can be approved with Face ID.
What you need first
- A Mac, since the notch app and most features are macOS only
- Download the Coucou app from the releases page linked in the README
- An AI coding agent such as Claude Code, Codex, Cursor or Gemini CLI
- Your own API keys for any cloud provider you plan to use, stored in the macOS Keychain
- An iPhone with the Coucou iPhone app, only for the phone features
Steps
- Set up Coucou on the Mac and sign in with the iCloud account used by the iPhone app.
- Install the Coucou iPhone app and allow notifications.
- Start an agent session on the Mac, such as Codex, Cursor or Gemini CLI.
- Lock the Mac and watch the agent state in the Live Activity on the iPhone.
- Tap Allow or Deny from the Lock Screen and confirm with Face ID.
Prompt for your agent
Using the Louis-CFM/coucou repo, set up the Coucou Mac app and iPhone app so that a Codex session on <target Mac> shows as a Live Activity on <target iPhone>. Expected output: the agent state appears on the Lock Screen, and an Allow tap is confirmed with Face ID. Verify that the Mac applies only the decision for the request it is waiting on.
Caveat. The README does not list the iPhone app install route or the setup for iCloud sync, so those steps need to be checked in the repo before use.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page