agentacct vs cc-lens
Local-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. — versus — npx 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.
cc-lens is analytics over ~/.claude: session replay, cache and cost breakdowns, budgets, team adoption. Agentacct is cross-harness and receipt-shaped, built around a lifecycle that separates what the agent claimed from what was proven. Dashboard versus audit record.
| agentacct | cc-lens | |
|---|---|---|
| Stars | 667 | 588 |
| Forks | 75 | 80 |
| Language | Python | TypeScript |
| License | MIT | MIT |
| Last activity | today | 2 months ago |
| Topics | coding, local | coding |
| Curated connections | 7 | 6 |
agentacct — the curator's take
The only tool in this neighbourhood that refuses to take the agent's word for it. Everything else here counts tokens and dollars; agentacct counts work and evidence, and keeps them on separate axes — an agent saying 'done' files the task under Reported, and only a machine check that postdates the newest recorded work earns Verified. Every figure wears its basis (`≈` for estimated, bare ` only for reported), every field carries provenance (client hook, transcript scan, MCP record), and unconnected verifier sources stay honestly labelled 'not connected' instead of quietly scoring zero. macOS app, `agentacct tui`, and a loopback-only JSON API; no account, no telemetry, never touches your provider key. Use it when you are accountable for agent output. Overkill if you only want to know this month's spend.
cc-lens — the curator's take
The zero-friction option among Claude Code dashboards: one npx command, loopback-bound by default, and v0.4's Insights tab actually recommends actions — cache, model choice, compaction, plan-fit and budget opportunities mined from your own usage — instead of just charting it. Team mode (shared-folder push hub + terminal digest) is a real differentiator for leads tracking adoption. Costs are estimates from a local pricing table (`~/.cc-lens/pricing.json` to override) — treat them as directional and keep the table current. Claude-only; for subagent forensics and ticket linking, claude-code-karma digs deeper; for a number next to your clock, ai-token-monitor.