Who it is forA developer running Claude Code or Codex all day who keeps hitting usage limits mid-task and wants to see remaining quota without opening a terminal.
The problemQuota is invisible until a long agent task fails halfway through, because the numbers sit in a terminal window you are not watching.
The outcomeA panel on your desk shows Claude's weekly and heaviest-model weekly quota and Codex's weekly quota, each with a reset countdown and today's burn.
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
- Read What you need in the README and confirm you have an ESP32-S3 AMOLED board or will use the simulator.
- Follow the Setup, the vibecoder way section with your coding agent, one verified step at a time.
- Run the host service on your Mac or Windows PC and connect the panel to the same Wi-Fi network.
- Check the Usage page on the glass and confirm Claude and Codex weekly quota with reset countdowns appear.
- Leave local mode on so agent activity stays on your LAN and no VibePulse account is needed.
Prompt for your agent
Using the niclasvestlund-YT/vibepulse repo, help me set up the Usage page for <my board model or simulator> following the Setup, the vibecoder way section. Expected output: a panel showing Claude weekly and Codex weekly quota with reset countdowns. Verify that the Usage page updates after one real Claude Code or Codex request.
Caveat. The README says the Windows core and physical answer loop were verified only at the v1.0.0 host runtime, so check the host support matrix before relying on a Windows setup.
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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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