tokenmaxxing: track AI coding usage across tools and devices

Alexandru Turcanu — Thu, 01 Oct 2026 22:08:06 +0000

If you use more than one coding agent, or work across multiple machines, your usage history ends up scattered across local logs.

tokenmaxxing is our open-source CLI and public leaderboard for bringing those daily totals together. It builds on ccusage and syncs usage to one public profile.

What it does

Combines usage from multiple devices without counting the same daily upload twice.
Tracks token counts and API-equivalent cost by coding agent and model.
Provides a public profile with usage history and a leaderboard with 7-day, 30-day and all-time views.
Supports Claude Code, OpenAI Codex, OpenCode, Gemini CLI, GitHub Copilot CLI and other agents listed in the repository.

The cost figures are API-equivalent estimates. They are not necessarily what you paid, especially if you use a subscription.

Try it

Install the CLI, then run the setup command:

npm install -g @851-labs/tokenmaxxing@latest
tokenmaxxing bootstrap

The setup signs you in, syncs the usage already on your machine, offers to install automatic syncing, and opens your public profile. You can run it on each machine you use.

To inspect exactly what a sync would send:

tokenmaxxing sync --dry-run

What gets uploaded

Only daily aggregates: date, model, agent, token counts and API-equivalent cost. Prompts, source code, file paths, project names and session content stay on your machine.

Your profile and leaderboard totals are public, so this is intended for people who want to share their usage. Device hostnames are only visible to you in settings and your per-device breakdown.

Open source

The CLI's background service supports macOS, Linux and Windows. The project is MIT-licensed, and the implementation is available on GitHub.

You can explore the leaderboard at tokenmaxxing.sh. I'd be interested in feedback on which views make multi-agent usage easier to understand.

The making of "Simon Draws!"

Alexandru Turcanu — Sat, 23 May 2020 14:35:14 +0000

Introduction

"Simon Draws!" is one of the last projects I've worked on while being a high-school student. This project started out as my submission for this year’s WWDC. Every year Apple creates a Swift Student Challenge (also known as a Scholarship), where students are encouraged to showcase their love of coding and creativity through a 3 minutes playground app.

Idea

This project is a fun game of memory 🧠 combined with drawing ✍️ that integrates on device machine learning to create a personalized experience for each user. Here's the gist of it:

First of all, you will have to tell Simon which theme of symbols you prefer.
Draw each symbol a couple of times, so that Simon can familiarize and understand your drawing style.
Afterward, you will be shown a sequence of symbols and your task is to draw them in the same order as they are presented to you.
Play. Repeat. Play 😝

You can checkout a youtube video that showcases the game.

How I built it?

The development has been split up into 3 core parts:

UI & UX
Drawing Canvas
Machine Learning Model

1. UI & UX

The primary UI framework is SwiftUI. Its functional programming and state paradigms made it a breeze to keep track of game states and create "liquid smooth" animations.

Furthermore, to create an immersive experience while playing, I've added sound effects to most of the user interactions using AVFoundation. An example of this is the sound of a pencil scratching a paper while drawing or the "whoosh" transition.

2. Drawing Canvas

Since this is an app that revolves around the user drawing symbols, it meant that the drawing canvas is an essential part of the user interface. Through careful and intentional design, I've made all of the interactions, like picking, playing, and restarting, available via the canvas interface.

Regarding the actual implementation, PencilKit not only enabled the user to make his own sketches, but also create a genuine and natural drawing experience.

3. Machine Learning Model

The ML Model is a drawing classifier that recognizes new drawings based on a K-Nearest Neighbors model (KNN). By using on device machine learning, the model gets updated in real time and creates a personalized experience for each user.

Try it yourself! 🕹

If you feel like trying the game yourself you can find all of the source code and steps to install on Github.

Pondorasti / SimonDraws

"Simon Draws!" is my Swift Student Challenge Submission for WWDC2020 [Accepted!]

SimonDraws

A Swift Playground created by Alexandru Turcanu during May 2020

About

"Simon Draws!" is a game of memory 🧠 combined with drawing ✍️.

By using on-device machine learning Simon can learn in real-time how you draw symbols and create a personalized experience for each user.

You can checkout the youtube video 📺 or download the .playgroundbook file and import it to Swift Playgrounds on iPad.

How to play

First of all, you will have to tell Simon which theme of symbols you prefer and then draw each icon a couple of times, so that Simon can familiarize with your drawing style.

Afterward you will be shown a sequence of icons and your task is to draw them in the same order as they are presented to you.

Play. Repeat. Play 😝

License

"Simon Draws!" is available under the MIT license. See the LICENSE file for more info.

View on GitHub

DEV Community: Alexandru Turcanu