🔥CodeBurn
getagentseal/codeburn · homepage ↗
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
⭐ Popular: 9k stars, gaining about 209 a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- Gives developers and teams a single view of AI coding token spend across 31 tools including Claude Code, Cursor, Codex and Gemini, broken down by model, project and task.
- Runs fully local with no API keys, no cloud upload and no proxy, so cost tracking does not add a data-exfiltration surface.
- The optimize command surfaces concrete waste patterns like re-read files across sessions, low edit-to-read ratios, uncapped bash output and unused MCP servers.
under the hood
- Written in TypeScript with a Swift component for the macOS menu bar app, requiring Node.js 22 or later.
- Reads session files from each tool's own on-disk location, for example Claude at ~/.claude/projects and Cursor via a SQLite database using better-sqlite3, rather than intercepting traffic.
- Classifies work into 13 categories using deterministic pattern matching with no LLM calls, prices usage from LiteLLM data refreshed daily, and converts currencies via Frankfurter exchange rates.
Radar summary, generated from the project's public sources
star history
- PR#32 1k 2026-04-22
- now 9k + 8k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Quietly building: more output than attention, for now.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Token and cost observability for AI coding
similar projects
compare these →- 🐑 herdr
Rust · 3.1× the stars
the runtime your coding agents live on
30k ACTIVE - 💻 Superset
Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
13k ACTIVE - ⚡ RTK
Rust · 8.1× the stars
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
76k ACTIVE
comments
Sign in with GitHub to add your blip on CodeBurn.