codeburn vs tare
Local-first cost ledger for AI coding: reads the session files 36 tools already write and breaks every token and dollar down by task, model, project. TUI, web, desktop, menubar — no proxy, no keys. — versus — Claude Code skill that reads your local session logs and answers 'where did my tokens go' in plain English: deduplicated totals, cost charged to the tool that caused it, 5-hour window state.
Both are local-first cost ledgers built from session files already on disk. Codeburn spans 36 tools for breadth; tare goes deep on one — causal attribution and rolling-window forensics that only work if you model a single harness's log format precisely.
| codeburn | tare | |
|---|---|---|
| Stars | 9.8k | 161 |
| Forks | 776 | 8 |
| Language | TypeScript | Python |
| License | MIT | MIT |
| Last activity | today | 3 days ago |
| Topics | coding, local | coding, skills, local |
| Curated connections | 4 | 7 |
codeburn — the curator's take
The honest architecture for spend tracking — read the session files already on disk, no proxy in your API path, nothing leaves the machine — executed at the broadest scope in the category: 36 tools, four surfaces, one data source. The parts beyond pretty dashboards earn the install: waste detection with applyable (and undoable) fixes, budget guards, model comparison. Limits are inherited from the source: it sees what session logs record, and subscription flat fees vs metered API blur what a 'dollar' means — treat per-task cost as a good estimate, not accounting (pricing via LiteLLM's daily refresh). When NOT: single-tool Claude Code forensics — cc-lens and claude-code-karma go deeper there with replay and cache breakdowns.
tare — the curator's take
Install it the day you get rate-limited and can't explain why. Two things make it better than the usual token dashboard: it deduplicates Claude Code's repeated response records (~86% inflation on the author's data), and it charges tokens to the tool that *caused* the re-sends rather than the one that returned bytes — which is how one big early file read quietly dominates a week. It is diagnosis, not control: no budgets, no blocking, no compaction, nothing changes your behaviour for you. Claude Code only, so multi-harness shops want a cross-CLI ledger instead. Everything stays local, and SECURITY.md tells you which greps verify that.