junhoyeo/tokscale

🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of tokens tracked.

What it solves

Tokscale provides a centralized way to monitor and analyze token consumption and costs across a wide variety of AI coding agents and IDEs. It eliminates the need to manually track spending across different tools like Claude Code, Cursor, GitHub Copilot CLI, and others, by aggregating usage data from local logs and databases.

How it works

Tokscale scans local data locations (such as SQLite databases, JSONL files, and cached CSVs) used by various AI coding clients to extract token usage. It integrates with LiteLLM's pricing data to calculate real-time costs, including support for tiered pricing and cache token discounts.

Who it’s for

Developers who use multiple AI coding assistants and want a high-performance CLI tool and visualization dashboard to track their total AI spend and token usage.

Highlights

  • Broad Client Support: Supports a massive list of AI agents including Claude Code, Cursor, GitHub Copilot CLI, Zed Agent, and many others.
  • Real-time Pricing: Uses LiteLLM's pricing data for accurate cost calculations.
  • TUI Dashboard: Includes a terminal user interface for viewing daily summaries, model stats, and usage reports.
  • Visualization Frontend: Offers a 3D contributions graph and a social platform for submitting usage data to a leaderboard.
  • Sync Commands: Specialized commands to sync data from tools like Trae, Warp, and Antigravity.

Related

  • Project
    stormzhang/token-tracker

    A local token consumption and cost tracking tool for AI agents like Claude Code, Codex, and Kimi Code, featuring real-time status bars and detailed usage analytics.

  • Project
    xiufengsun/TokenTracker

    Token Tracker is a local‑only dashboard and desktop app that automatically records how many tokens you spend with 38 AI coding tools (Claude, Gemini, Copilot, Cursor, etc.). It shows usage trends, model‑wise cost estimates, heat‑maps, widgets, a pet companion, achievements, and optional cloud sync/leaderboard – all without requiring an account or sending prompts to any server.

  • Project
    VasiHemanth/tokentelemetry

    A local observability dashboard that tracks token usage, LLM costs, and session traces for AI coding and autonomous agents by reading their local log files.

  • Project
    soulduse/ai-token-monitor

    A lightweight system tray app for macOS and Windows that tracks real-time token usage and costs for AI coding tools by parsing local session logs.

  • Project
    getagentseal/codeburn

    CodeBurn is a free, open‑source Node.js utility that locally reads session logs from dozens of AI coding tools (Claude, Cursor, Codex, Gemini, etc.) and shows you exactly how many tokens and dollars each model, project, and task has consumed. It provides a terminal UI, a web dashboard, and a menubar/tray app, can detect waste patterns (re‑reads, low read‑to‑edit ratios, unused agents, etc.), suggest and apply fixes, enforce budget caps, compare model efficiency, and even correlate spend with git commits. All processing stays on your machine; no API keys or data are sent elsewhere.