AI product Open source

Headroom

Headroom is a local-first macOS menu-bar app for monitoring AI coding quotas and software delivery status, with optional iPhone, iPad, Apple Watch, and ESP32 desk-display clients. A Python host running on the Mac reads the authentication data and command-line tools already configured for services such as Claude, Codex, Cursor, GitHub, and Vercel, then serves a single local JSON feed; credentials remain on the machine and no Headroom cloud account is required. Its interfaces show provider quota meters, usage rings, burn rate and spend, failed Actions, deployments, monitors, and other attention items, and the iPhone client can approve, deny, or reply to Claude and Codex requests without starting work. The Mac host uses port 8737, requires macOS 14+ and Python 3.9+, and the optional desk display uses a Waveshare ESP32-S3-Touch-AMOLED-1.8 board.

View repository Mentioned in 2 videos ↓

What Headroom is used for

2 uses taken from transcripts — each links to the moment in the video.

  • Shows AI coding quotas, deployment health, failed builds, and service alerts in macOS, iPhone, Apple Watch, or optional ESP32 interfaces by reading existing local tool sessions.

  • Compresses tool outputs, logs, and other context before they are sent to a model, while caching compressed content locally so it can be retrieved later.

Videos mentioning Headroom

2 in the library.