Building a Multi-Agent Token Usage Widget in Under 500 KB

A developer built Leap EDGE, a macOS desktop quota monitor for parallel AI coding subscriptions (Gemini via Google Antigravity, Claude Code, OpenAI Codex, GitHub Copilot) that computes burn rate and projected run-out time from used-versus-elapsed quota fractions. Shipped as a 483 KB Swift dual-engine universal binary, it avoids an embedded WebView by default, drawing five quota cards with AppKit and NSBezierPath and polling data every 300 seconds, versus roughly 220 MB for Electron and 6 MB for Tauri v2.

Series 2/2: Multi-Model Collaboration & Quota Management in Practice Part 1: Building a Cross-Model Collaborative Workflow with Google Antigravity https://dev.to/gde/building-a-cross-model-collaborative-workflow-with-google-antigravity-2jj5 When you run tasks in parallel across Google Antigravity Gemini , Claude Code , OpenAI Codex , and GitHub Copilot , a progress bar that simply says 40% used is not very useful. Burning 40% in the first 30 minutes of a 5-hour quota window means you will hit a wall in another hour; burning 40% with 20 minutes left before reset means you have more quota than you can finish. To make an always-on desktop quota monitor answer "At my current pace, how much longer can I keep working today?" , I worked with the agents to build two things: paceFraction 0.0% . To know whether a quota pool is about to blow up—or whether it still has plenty of slack—you only need to compare two ratios: usedFraction usedFraction = consumed / total paceFraction = 1.0 - resetsAt - now / windowDuration rate = usedFraction / paceFraction projectedRunOut = windowStart + windowDuration / rate For example: suppose a 5-hour window starts at 09:00 and resets at 14:00 . At 10:00 , one-fifth of the window has passed paceFraction = 20% , so the white tick sits at 20% . If you have already used 40% by then, your burn rate is 2x the sustainable pace rate = 2.0 . At that speed, your entire quota will bottom out 5 / 2 = 2.5 hours after the window started—at 11:30 . So on each Leap EDGE card: rate 1.15 , the bar shifts color and lights up a red pill: ▲ RUNS OUT 11:30 . ⏱ LASTS TO RESET . With a single glance, you immediately know whether to route the next heavy task to another AI subscription. All of this came out of iterating back and forth with Gemini 4 Argon while designing and tuning the implementation. I already had a 22 KB vanilla HTML/CSS/JS web dashboard ?mode=edge . My initial idea was to wrap it in Tauri v2 Rust + system WebView as a desktop widget for macOS and Linux. However, this widget isn't used like a normal app: you don't open it for five minutes and close it—it stays pinned to your desktop all day as a background monitor. After looking into how macOS handles WebView processes, I decided not to put a WebView in the default path: | Dimension | Electron | Tauri v2 Rust + WKWebView | Leap EDGE Swift Dual-Engine Universal Binary | |---|---|---|---| | Binary size | ~220 MB | ~6 MB target/ build cache ~800 MB | 483 KB arm64 + x86 64 combined | | Persistent processes | 4+ Chromium | 3 Host + WebKit.WebContent + GPU | 1 pure CoreGraphics by default, zero WebKit | | Background wakeups & App Nap | High idle drain | 1s JS setInterval clock keeps waking IPC | 300s data poll + 60s clock tick with 5s tolerance | | macOS desktop integration | Needs plugins | Requires objc2 FFI for low-level window flags | Native 1-line desktop-level pinning & 👻 Click-Through | According to Apple's WebKit WKProcessPool documentation https://developer.apple.com/documentation/webkit/wkprocesspool and the Apple App Nap Power Efficiency Guide https://developer.apple.com/library/archive/documentation/Performance/Conceptual/power efficiency guidelines osx/AppNap.html , simply instantiating a WKWebView spawns separate web-content and rendering subprocesses; on top of that, a 1-second JavaScript setInterval for a live clock keeps waking the rendering pipeline. Just to draw five fixed-format dark quota cards, the default path doesn't need a browser engine running 24/7. So we built a dual-engine switch inside a single leap-edge.swift file: /api/usage JSON and draws the five cards Copilot, AGY, Claude Pro/Team, Codex plus live macOS Menu Bar indicators using AppKit and NSBezierPath . Idle CPU stays at window.ignoresMouseEvents = true so mouse clicks pass straight through to the Terminal or IDE behind it. WKWebView 🌐 Web Mode removeFromSuperview and sets the instance to nil , returning all WebKit subprocess memory to the OS. With both Macs covered, I also have two Ubuntu machines on my desk: a ThinkPad X1 Carbon , and a Surface Pro 7 used for demos and meetings. On Linux, we applied the exact same philosophy—a single-file, zero-third-party-dependency leap-edge.py that supports two modes: leap-edge.py --status and --json --gui Looking back at this two-day build, the biggest win wasn't saving a few dozen megabytes of RAM—it was clarifying two things: Thanks for reading.