Track your AI usage across Claude Code, Cursor, ChatGPT, Gemini, and more
Project description
Token Hoggers
Gamified, tool-agnostic AI usage leaderboard. Track and compete on your AI usage across Claude Code, Cursor, Gemini, ChatGPT, Copilot, and more.
Inspired by claude_rank but tool-agnostic, with an RPG character system built on the AMI (AI Maturity Index) framework.
How It Works
- Install the CLI —
pip install tokenhoggers - Sign in — Google OAuth at tokenhoggers.ai
- Sync —
tokenhoggers syncreads your local AI tool stats (counts only, never content) - Compete — See your rank, level, tier, and RPG stats on the leaderboard
Privacy-First
We collect counts and timestamps only. Never prompt text, code, file paths, or API keys.
| Collected | Never Touched |
|---|---|
| Token counts (in/out) | Prompt/response text |
| Message & session counts | Project/repo names |
| Tool call counts | File paths, code, diffs |
| Model names | API keys, credentials |
| Timestamps | Working directories |
RPG Character System
Built on the AMI (AI Maturity Index) — 4 dimensions that measure how you use AI, not just how much.
MST (Mastery)
|
PRC ──────+────── VRS
|
END (Endurance)
| Stat | Measures |
|---|---|
| Mastery | Power-user behavior (tool calls/session, model diversity) |
| Precision | Output per effort (efficiency) |
| Versatility | Multi-tool range |
| Endurance | Consistency (streaks, active days) |
Tiers: Bronze → Silver → Gold → Platinum → Diamond
Supported Tools
| Tool | Data Source | Parser |
|---|---|---|
| Claude Code | ~/.claude/stats-cache.json |
CLI |
| Cursor | state.vscdb (SQLite, read-only) |
CLI |
| Gemini CLI | ~/.gemini/tmp/*/logs.json |
CLI |
| ChatGPT | Web request counting | Browser Extension |
| Gemini Web | Web request counting | Browser Extension |
| Claude Web | Web request counting | Browser Extension |
Quick Start
CLI
One-liner install (any OS, recommended — handles Python detection and PATH):
curl -fsSL https://tokenhoggers.ai/install.sh | sh
Homebrew (macOS):
brew install token-hoggers/tap/tokenhoggers
Python users (if you already have Python set up):
pipx install tokenhoggers # recommended — isolated install
# or
pip install tokenhoggers
Then use it:
tokenhoggers login # Sign in with Google (opens browser)
tokenhoggers status # Show what AI tool data we found locally
tokenhoggers sync # Send counts to the leaderboard
tokenhoggers sync --force # Re-sync all historical data
Desktop App (macOS)
Menu bar app that shows your stats at a glance.
cd desktop/src-tauri
source ~/.cargo/env
cargo run
Browser Extension
Tracks request counts on ChatGPT, Gemini, and Claude web (never captures content).
cd extension/icons && python generate.py
# Chrome → chrome://extensions → Developer Mode → Load unpacked → select extension/
Architecture
collectors/cli/ Python CLI — parses local AI tool stats
web/ Frontend (vanilla HTML/JS/CSS) — hosted on Vercel
supabase/ Backend — PostgreSQL, Auth, Edge Functions, Realtime
desktop/ Tauri 2.x macOS menu bar app
extension/ Chrome MV3 browser extension
Tech Stack
- Backend: Supabase (PostgreSQL + Auth + Edge Functions + Realtime)
- Frontend: Vanilla HTML/JS/CSS (Claude Rank-inspired design)
- CLI: Python 3.9+
- Desktop: Rust / Tauri 2.x
- Extension: Chrome MV3
Contributing
PRs welcome! See CONTRIBUTING.md.
License
MIT — see LICENSE.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file tokenhoggers-0.1.1.tar.gz.
File metadata
- Download URL: tokenhoggers-0.1.1.tar.gz
- Upload date:
- Size: 21.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a636658750949d97ca9369f1ba29d6dfca125e31cb081730261457d8bd762d42
|
|
| MD5 |
b4bd60c133bef0212ee81c4b8f6583b4
|
|
| BLAKE2b-256 |
28eedfee337cce326e9ac769f6ec7b8a50e0c9f2c6ebf232a96c2442a4d0aaa5
|
File details
Details for the file tokenhoggers-0.1.1-py3-none-any.whl.
File metadata
- Download URL: tokenhoggers-0.1.1-py3-none-any.whl
- Upload date:
- Size: 23.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
22c4d064a2a86243dbbc2f49106c241bd6d03ccbb682bcd8839628c45d9ec9e1
|
|
| MD5 |
b8c099698d38c56f309cf33c3b3b741d
|
|
| BLAKE2b-256 |
5e62803d16ec5809f6ab9de8db696eea22c5cf8f2184bfa393cb5a0b3c3b9c84
|