claude-code-karma vs tare
Local-first dashboard over ~/.claude — sessions, timelines, per-session costs, tool/agent/skill/plugin analytics, live activity via hooks, and ticket linking. No cloud, no telemetry. — 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 read ~/.claude locally with no cloud. Karma is a dashboard you go and browse; tare is a question you ask inside the session and get a diagnosis and a recommendation back. Pick by whether you want charts or an answer.
| claude-code-karma | tare | |
|---|---|---|
| Stars | 321 | 161 |
| Forks | 32 | 8 |
| Language | Python | Python |
| License | Apache-2.0 | MIT |
| Last activity | yesterday | 3 days ago |
| Topics | coding | coding, skills, local |
| Curated connections | 5 | 7 |
claude-code-karma — the curator's take
Your ~/.claude directory is a goldmine Claude Code never shows you — Karma turns the JSONL into browsable sessions with full chronological timelines, cost and cache-hit breakdowns, subagent trees, and a surprisingly complete inventory of every plugin, skill, and hook you've installed with usage stats. Read-only ticket linking (Linear/Jira/GitHub) is the team-ready touch. Know the limits: Claude Code prunes session data after ~30 days, so history evaporates unless you keep Karma indexing; it's a two-process dev setup (FastAPI + SvelteKit), not a single binary; and it's Claude-only — no Codex/OpenCode. Pair with ai-token-monitor when all you want is the spend number next to your clock.
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.