█

AI/TLDR

CodeBurn

Local token and cost accounting across 41 AI coding tools

GitHub★ 11.1kWebsitecodeburn.app
Observability & LLMOpsOpen source
Language
TypeScript
License
MIT
$npx codeburn

Overview

CodeBurn answers a question most LLM observability tools cannot: where your AI coding budget actually goes across every tool you use. Rather than sitting in the request path as a proxy, it reads the session files that coding agents already write to disk — Claude Code's JSONL transcripts, Codex rollouts, Cursor's and Zed's SQLite stores, Gemini CLI chat logs, Copilot session state and so on — and reconstructs spend from them. No API keys, no proxy, and nothing leaves the machine.

Coverage spans 41 tools and agents including Claude, Cursor, Codex, Copilot, Gemini, Grok, Cline, Goose, Crush, Warp, Roo Code, Kilo Code, Qwen, Kimi, OpenCode and Zed. Breakdowns run by model, provider, project, task category and activity type, with input, output, cache-read and cache-write tokens counted separately — the distinction that usually explains a surprising bill.

It also goes past accounting into diagnosis. A one-shot rate measures how often edits land without retries; waste detection flags re-read files, low edit ratios, unused MCP servers and bloated configs; yield tracking correlates spend against git commits to separate productive work from abandoned or reverted code. Findings can be applied interactively with full undo. Interfaces include a terminal TUI, a web dashboard, a native desktop app and a menubar widget.

What it does

  • Reads session files already on disk across 41 coding tools — no API keys, proxy, or data egress
  • Cost and token breakdowns by model, provider, project, task category and activity type
  • Separate input / output / cache-read / cache-write token accounting
  • One-shot success rate and retry-cycle measurement per tool and model
  • Waste detection (re-read files, low edit ratios, unused MCP servers, bloated configs) with interactive, undoable fixes
  • Yield tracking against git history, plus optional budget caps and alerts for Claude Code sessions
  • Terminal TUI, web dashboard, desktop app and menubar/tray widget

Getting started

CodeBurn needs Node.js 22.13+ and at least one supported tool with session data already on disk. There is nothing to configure — it discovers the sessions itself.

Run it

npx is enough for a first look; install globally to keep it around.

bashbash
npx codeburn

Install globally

Puts the codeburn command on your PATH.

bashbash
npm install -g codeburn

Open a richer view

The web dashboard and the menubar widget are alternatives to the terminal UI.

bashbash
codeburn web
codeburn menubar

Find and fix waste

optimize surfaces findings and can apply them interactively, with undo.

bashbash
codeburn optimize

Compare models and check yield

compare puts model efficiency side by side; yield correlates spend with git commits to show productive versus abandoned work.

bashbash
codeburn compare
codeburn yield

Commands and code are distilled from the project's own documentation — always check the official repo for the latest.

When to use it

  • Find out which model and which project are responsible for an unexpected AI coding bill
  • Compare one-shot edit success rates between models before standardising a team on one
  • Audit AI spend without routing any traffic through a third-party proxy or handing over API keys
  • Separate spend that turned into merged commits from spend on work that was reverted or abandoned

How CodeBurn compares

CodeBurn alongside other open-source observability & llmops tools AI/TLDR tracks, ranked by GitHub stars.

ToolStarsWhat it does
Langfuse★ 34.8kA self-hostable platform for tracing LLM and agent calls, managing prompts, and running evaluations to debug and improve AI applications.
Opik★ 22.1kAn open-source platform from Comet for tracing, evaluating, and monitoring LLM applications, RAG systems, and agent workflows with dashboards and LLM-as-judge metrics.
RagaAI Catalyst★ 16.2kPython SDK that combines agentic tracing, metric evaluation, dataset and prompt management, guardrails and red-teaming for LLM and multi-agent applications.
TensorZero★ 11.7kAn open-source LLMOps platform that puts a single gateway in front of every major LLM provider and adds observability, evaluation, optimization, and A/B testing.
CodeBurn★ 11.1kLocal token and cost accounting across 41 AI coding tools
Evidently★ 7.9kA monitoring and evaluation framework for ML and LLM systems that tracks output quality, drift, and test results over time with reports and dashboards.
OpenLLMetry★ 7.4kAn OpenTelemetry-based SDK that auto-instruments LLM providers, vector databases, and frameworks so traces flow into any existing observability backend.
Helicone★ 6.2kA proxy-based observability platform that logs, monitors, and evaluates LLM API calls by routing requests through its endpoint with one line of code.