Tracks token burn and water cost locally when no one else measures impact.
Developers using local AI coding agents
WakaTime · CodeStats
[WHAT THIS IS] A local token usage tracker that works across different coding harnesses and estimates energy and water impact
[MY EXPERIENCE] Tracking this really put things into perspective. My personal usage is close to 1 MWh in the past three months which I had no idea about. This does not include my AI usage at work which is probably 10x.
[DEMO] If you are interested in tracking these numbers locally, try out: https://ai-meter.app
- It reads historical data if the files are present. Works completely locally (except to check if there is an update for the widget) - No login. No analytics. No tracking.
----
[On estimates]
AI Meter measures tokens from local AI coding-tool logs, then estimates:
Electricity: tokens ÷ 1M × 0.39 kWh, calibrated from Oviedo et al.’s production-scale inference model.
Direct cooling water: electricity ÷ 1.20 PUE × 0.45 L/IT-kWh, using LBNL’s U.S. data-center WUE scenario.
These are adjustable estimates, not provider measurements. They exclude training, hardware manufacturing, electricity-generation water, and local-device energy.
----
Hope you find this interesting! Please feel free to give feedback, would love to make this better!
You enter monthly meter readings and MeterLogs turns them into grouped yearly dashboards (electricity, water, gas, solar production/feed‑in) — a deliberately pragmatic, no-hardware play. The site leans on trust signals (GDPR, Made in Germany) and a tidy starter flow, but it'd win more converts with CSV import, easier mobile entry, or optional utility integrations.
Notebook calculates water usage per token, but lacks interactive tooling.
Unified local AI cost tracker when native dashboards stay siloed and cloud-based.
Reads Copilot's internal session files for real token counts, not estimates.
Zero-network meter parses local CLI transcripts so nothing ever leaves your machine.
Reads local logs instead of flaky API calls—finally accurate token tracking.
