Who it is forA developer who runs agents in another window and loses long stretches of time when an agent quietly waits on a yes or no question.
The problemAn agent asks one question and then sits idle, often for twenty minutes, because you are in a different window and cannot see it.
The outcomeWhen an agent blocks on your input, the screen switches to a full-screen NEEDS YOU alert in that provider's colour, naming the project it is waiting on.
What you need first
- An ESP32-S3 AMOLED board with a core, or the simulator for a no-hardware run
- A Mac or Windows PC to run the pure-stdlib Python host service
- A Claude Code or Codex account whose usage you want to monitor
- Wi-Fi shared by the computer and the panel for local mode
Steps
- Set up the panel and host service as described in the Setup, the vibecoder way section.
- Keep the panel within reach of your desk so the alert is visible from across the room.
- Start a Claude Code or Codex task that needs a yes or no answer from you.
- Confirm the NEEDS YOU alert names the correct project and shows the provider colour.
- Tap the panel to dismiss the alert, or use the answer flow if you have enabled the Needs You bridge.
Prompt for your agent
In the niclasvestlund-YT/vibepulse repo, trigger a test NEEDS YOU alert by running a Claude Code or Codex task that asks for a confirmation. Expected output: the panel turns into a full-screen NEEDS YOU screen naming the project. Verify the alert appears on the glass within a short time after the agent blocks.
Caveat. The README describes the NEEDS YOU alert as part of the core loop that was physically exercised on macOS and Windows, but alert timing on your own setup still needs your own check.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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