Agent Usage
Every AI coding limit, one glance — native Mac widgets
What it does
Every AI coding subscription, one glance. A native macOS dashboard + Desktop widgets for Claude, ChatGPT, OpenCode, Command Code and Z.ai. • Native SwiftUI + WidgetKit — widgets stay fresh on their own • Honest states — real snapshots, never fake 0% or fake freshness • Honors server Retry-After; recovers when limits reset • Keychain-native, reuses your CLI login, auto re-imports expired tokens • Zero telemetry Free, open source (MIT), signed & notarized by Apple.
Agent usage widget for macOS. Contribute to juanlatorre/agent-usage-widget development by creating an account on GitHub.
A native macOS dashboard & widgets for your AI coding subscriptions. Stop guessing how much quota you have left. Agent Usage tracks your Claude, ChatGPT, OpenCode, Command Code and Z.ai limits in one place — with Desktop widgets that stay fresh on their own. Then: pick an account, connect it (paste a key or point it at your CLI config), and add the widget from your Desktop's widget gallery. git clone https://github.com/juanlatorre/agent-usage-widget.git cd agent-usage-widget open App/AgentUsage.xcodeproj # select the AgentUsage scheme, ⌘R The core logic lives in Packages/AgentUsageCore and is fully self-contained: swift test --package-path Packages/AgentUsageCore # 233 tests 🧠 How it works…from github.com
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com