Author

aiterms

OpenUsage Community: track every AI coding subscription from one menu bar

OpenUsage Community is a lightweight desktop app that pulls your usage and quota from 25+ AI coding services — Claude, Copilot, Cursor, Codex, Gemini, Grok and more — and shows them together in your menu bar or system tray, so you never have to open a single provider dashboard to know where you stand.

It is an independent, community-maintained continuation of the original OpenUsage project. The community fork was created after the original moved toward a Swift / macOS-first direction; this version keeps a cross-platform footing (Tauri + Rust + TypeScript) with strong Linux support.

Why it matters

If you pay for more than one AI coding tool, your spend and your limits are scattered across separate dashboards. By the time you notice you're about to hit a cap — or that a subscription is barely used — you've already lost the context. OpenUsage Community collapses all of that into one always-available panel: progress bars, badges, and clear labels, "no mental math required." It's the kind of small utility that quietly saves you from rate-limit surprises mid-session.

What it does

• One unified view across 25+ providers, including Amp, Antigravity, Claude, Codex, Copilot, Cursor, Factory/Droid, Gemini, Grok, JetBrains AI Assistant, Kiro, Kimi Code, MiniMax, OpenCode, Windsurf, and Z.ai.
• Lives in the menu bar / system tray — toggle the panel from anywhere with a global keyboard shortcut.
• Auto-refresh on a schedule you choose, so the numbers stay current without manual polling.
• Export your history to CSV or Excel for your own reporting or budgeting.
• Local HTTP API at 127.0.0.1:6736, so you can script against your usage data or feed it into other tools.
• Proxy support via SOCKS5 or HTTP for restricted networks.
• Plugin architecture — new providers can be added without rewriting the app, which is why coverage keeps growing.

How it works

Under the hood it's a Tauri application: a Rust backend that talks to each provider's usage API, with a TypeScript front end for the panel (WebKitGTK handles rendering on Linux). Because each provider is a plugin, the app queries them independently and renders the results as a single dashboard. The same data is exposed on the local API endpoint, so the menu-bar UI and any script you write are reading from the same source.

Getting it

Prebuilt binaries are available for macOS (Apple Silicon and Intel) and Linux (AppImage, .deb, .rpm, installable via apt / dnf). Windows support is on the roadmap. Grab a release from the GitHub repo:

GitHub

GitHub - openusage-community/openusage: Community-driven continuation of OpenUsage. We are building the best AI usage tracker for Linux, macOS, and Windows - open, practical, and made together with the community 🚀💚

Community-driven continuation of OpenUsage. We are building the best AI usage tracker for Linux, macOS, and Windows - open, practical, and made together with the community 🚀💚 - openusage-community...

When it's a good fit (and when it isn't)

Reach for it if you juggle several AI coding subscriptions and want a single, glanceable source of truth for limits and usage. It's less useful if you're all-in on exactly one tool whose own dashboard you already watch — though even then, the CSV/Excel export and local API can be handy for tracking spend over time. As with any tool that reads your provider accounts, review which credentials each plugin needs before enabling it.

同じ著者の記事

What is speculative decoding?

Speculative decoding is a text-generation trick that lets a fast “draft” model propose several next tokens and then uses a larger “target” model to verify them, often reducing end-to-end latency without changing the final output distribution. Autoregressive LLMs normally generate one token at a time, and each token requires a full forward pass through the big model. That is accurate, but it can be slow. Speculative decoding matters when you want lower latency or higher throughput without switchi

papoo.work

What is tokens per second (throughput)?

Tokens per second, or throughput, is the rate at which a language model generates or processes tokens over time. Throughput is a practical way to describe model speed. If you care about user experience, cost efficiency, or server capacity, tokens per second tells you how much text the system can handle in a given time. You’d use it when comparing models, sizing infrastructure, or setting expectations for streaming responses. In practice, teams often care about both throughput and latency

papoo.work

What is time to first token (TTFT)?

Time to first token (TTFT) is the time between sending a generative AI request and receiving the model’s first output token. TTFT is the part of latency users feel first. If it is high, the system can seem “stuck” even if the full answer eventually streams quickly. You usually care about TTFT when you want: a responsive chat or copilot experience good perceived performance in streaming UIs to compare serving setups, models, or prompts to separate “slow to start” from “slow to finish” In practice

papoo.work

What is streaming (token streaming)?

Streaming, or token streaming, is when an AI model sends you its output incrementally as it is generated instead of waiting until the whole answer is finished. This solves the “dead air” problem: users see text quickly, which makes apps feel faster and more interactive. It is especially useful for chatbots, copilots, and any UI where a short time-to-first-token matters more than waiting for the full response. In practice, teams use streaming when they want: faster perceived latency, a typing-lik

papoo.work

What is batching / continuous batching?

Batching is the practice of grouping multiple requests together so a model can process them more efficiently, and continuous batching is the version where new requests are added to that group while others are still running. Large models are expensive to run because the same GPU is often underused if you serve one request at a time. Batching improves throughput by sharing compute across many requests. Continuous batching goes a step further: it keeps the GPU busy by letting the server dynamically

papoo.work

What is an inference endpoint / serving API?

An inference endpoint, or serving API, is a network service you send inputs to in order to get model predictions back in real time. It solves the problem of turning a trained model into something applications can actually use. You reach for an inference endpoint when you want: a web or mobile app to call a model on demand a backend to classify, rank, summarize, or generate text without running the model itself a standardized way to deploy, scale, monitor, and secure model requests In practice, m

papoo.work

What is quantization?

Quantization is the process of representing numbers with fewer bits, so a model or computation uses less memory and can often run faster. Large neural networks store weights, activations, and sometimes key/value caches as floating-point numbers. That is accurate, but expensive. Quantization reduces that cost by converting some of those values to lower-precision formats, such as 8-bit integers or even 4-bit representations. You usually reach for quantization when you want one or more of these: lo

papoo.work

What is distillation?

Distillation is a way to train a smaller model to imitate a larger, better one, so you keep much of the quality while reducing cost, latency, or memory use. Distillation solves a very practical problem: the model you want may be too slow, too expensive, or too large to deploy everywhere. You reach for distillation when you want one or more of these: lower inference cost faster responses smaller on-device models simpler deployment a model that approximates a stronger system without retraining fro

papoo.work

What is instruction tuning?

Instruction tuning is a way to train a language model to follow natural-language requests more reliably by fine-tuning it on examples of instructions paired with good responses. A base language model is good at predicting text, but that does not automatically make it good at doing what a user asks. Instruction tuning helps bridge that gap. You’d reach for it when you want a model to respond more helpfully to prompts like: “Summarize this email” “Write SQL for this schema” “Explain this code as i

papoo.work

What is RLHF?

RLHF, or reinforcement learning from human feedback, is a way to train a model so its outputs better match what people prefer, not just what is statistically likely. A plain language model learns to predict text. That is useful, but it does not automatically make the model helpful, honest, safe, or aligned with user intent. RLHF is used when you want to steer a model toward human preferences: better answers, fewer toxic outputs, more helpful refusals, and responses that fit product goals. In

papoo.work