getagentseal/codeburn

Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn

What it solves

CodeBurn addresses the lack of transparency in AI coding tool billing. While providers show total costs, they rarely detail how that spend is distributed across specific tasks, projects, or models, making it difficult for developers to identify waste or optimize their budget.

How it works

It is a local-first tool that reads session files already stored on your disk by AI coding tools. It uses pricing data from LiteLLM (refreshed daily) to calculate costs without requiring API keys, proxies, or wrappers. The tool provides several interfaces for viewing this data: a terminal-based dashboard (TUI), a local web dashboard, a macOS menubar app, and a GNOME Shell extension for Linux.

Who it’s for

Developers who use multiple AI coding agents and tools (such as Claude Code, Cursor, Codex, and Gemini) and want to track, analyze, and reduce their token usage and financial spend.

Highlights

  • Multi-tool Support: Tracks usage across 40 different AI tools and agents.
  • Waste Optimization: Scans for patterns like redundant file reads, low read-to-edit ratios, and unused MCP servers, providing ready-to-paste fixes.
  • Budget Guardrails: Allows users to set soft and hard cost caps on sessions to prevent unexpected overspending.
  • Model Comparison: Analyzes performance metrics like one-shot rates and retry rates to determine which model is most efficient for a specific user's workflow.
  • Yield Tracking: Correlates AI sessions with git commits to categorize spend as productive, reverted, abandoned, or ambiguous.
  • MCP Integration: Provides a Model Context Protocol (MCP) server so AI agents can analyze their own spending and suggest savings mid-conversation.

Related

  • Project
    xiufengsun/TokenTracker

    A local-first token usage and cost dashboard for 31 AI coding tools, featuring a desktop pet and native widgets for real-time monitoring.

  • 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
    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 reports.

  • Project
    junhoyeo/tokscale

    A high-performance CLI tool and visualization dashboard for tracking token usage and costs across multiple AI coding agents.

  • Project
    VasiHemanth/tokentelemetry

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