codeburn reads on-disk session files from 36 AI coding tools to compute token cost locally.

getagentseal/codeburn (8,922 stars, MIT, desktop v0.9.19) parses session files that coding tools already write to disk, analyzing input, output, cache-read, cache-write and web-search token counts to compute spend by model, project and activity, classifying usage into 13 task categories deterministically with no API calls. Repo description says 31 tools, README documents 36 — Claude Code, Cursor, Codex, Copilot, Gemini CLI, Mistral Vibe, Cline, Roo Code, Zed, Warp, OpenCode, Devin, Kiro and more, each with dedicated parsing logic. Everything local, nothing leaves the machine, which is what makes it usable on a work codebase where a metering proxy would be a non-starter.