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

> Source: <https://dev.to/gde/building-a-multi-agent-token-usage-widget-in-under-500-kb-1fih>
> Published: 2026-10-23 00:51:00+00:00

*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.