tareClaude 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.
Why switchBoth 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.
Full comparison → cc-lensnpx cc-lens: local analytics dashboard over ~/.claude — sessions with replay, cost and cache breakdowns, insights and budgets, team-adoption mode, a yearly Wrapped card. No cloud, no telemetry.
Why switchSame job — a local dashboard over ~/.claude JSONL. cc-lens is the one-command npx tool with insights, budgets and team adoption; Karma is the two-process forensic suite with subagent trees, hook/plugin inventories and Linear/Jira/GitHub ticket linking.
Full comparison → ai-token-monitorMenu-bar/tray app for macOS and Windows that reads Claude Code, Codex and OpenCode session logs and shows live token spend — per-model pricing with cache reads, plan-limit bars, webhook alerts.
Why switchBoth read the session logs your coding CLI already writes, at opposite depths: ai-token-monitor is the glanceable menu-bar spend counter with plan-limit alerts; Karma is the full forensic dashboard — timelines, subagents, tools, tickets.
Full comparison → agentacctLocal-first work receipts for coding agents: reads the session logs Claude Code, Codex, OpenCode and Hermes already write and reports what each task did, what it cost, and whether a check proved it.
Why switchSame local-first, no-cloud posture over ~/.claude with timelines, per-session costs and tool/skill/plugin analytics. Karma is Claude Code-centric telemetry; agentacct spans Codex, OpenCode and Hermes too and grades evidence rather than activity.
Full comparison →