Local-first · Claude Code + Codex · open source

One dashboard for every AI coding agent.

See exactly where your tokens go — cost, burn-rate, and how close you are to your plan's rate limit. No API keys. No cloud. Your data never leaves your machine.

⬇ Download for Windows ★ Star on GitHub
Free · no Python needed · native app + system tray · your data never leaves your machine
Unsigned for now — if Windows SmartScreen appears, click More info → Run anyway.

macOS & Linux

Native window · no security prompt · needs Python 3.10+
pip install --upgrade "burnmeter[app] @ git+https://github.com/cihanatak/BurnMeter" burnmeter
AGPL-3.0 open source Local-first · no cloud No API keys Claude Code + Codex Python 3.10+
Dashboard preview · the maker's real usage (v0.1.74)
Burnmeter dashboard: live burn-rate speedometer, today's spend, prevented cost, per-model breakdown, and recent sessions

Why Burnmeter exists

Neither Anthropic nor OpenAI exposes a real-time per-token usage API for individual Pro / Max / subscription plans. So if you're on a flat-fee plan, your local session logs are the only accurate source of truth for what you're actually burning. Burnmeter reads them and answers the one question that matters: "Am I about to hit the wall?"

Up and running in 30 seconds

No account, no API key, no config. It reads the logs your agents already write.

1

Install

pip install git+https://github.com/cihanatak/BurnMeter — pure-Python, stdlib-only core. No Docker, no database.

2

Run

burnmeter serve — auto-detects ~/.claude & ~/.codex, drops a Burnmeter shortcut on your desktop, and opens the dashboard in your browser.

3

Open

It opens at localhost:7654 on its own. If your browser doesn't pop up, click the link Burnmeter prints in the terminal — and if 7654 is already taken, it picks the next free port automatically. After that, just double-click the desktop icon.

Built for the question you actually have

Not a token accountant — a fuel gauge. Four things the other meters miss.

Rate-limit hero

For subscription plans the wall is the rate limit, not the dollar. A red ring at 90%+ tells you, in under a second, whether you can start that big task or you're about to get throttled — 5-hour and weekly windows, per device.

Burn-rate vs. your normal

"Is this run burning a lot or a little?" Your current $/hr against personal typical / busy / heavy reference zones, with a verdict like "3× faster than your usual." Efficiency, at a glance.

Cache-efficiency value

Cache reads cost ~10% of fresh input. Burnmeter shows your hit rate and the real dollars cache saved you — often the "I'm getting $50k of value for $200" number nobody else surfaces.

Per-project & per-model

Which repo is eating your quota, and which model is eating your dollars — at real per-model pricing (Opus/Sonnet/Haiku, GPT-5.5/5.4/Codex/mini). The model mix is the cost story.

Free core, forever

The whole local dashboard is open source. Pay only for services a single machine can't do alone — and you can always self-host the sync relay for free.

Free · OSS
$0
  • Full local dashboard, every agent
  • Rate-limit, burn-rate, cost projection
  • Cache-efficiency, per-project & git/branch attribution
  • Monthly budget · 30 days history · CSV export
  • Terminal statusline · config-file alert rules
  • AGPL-3.0, yours forever
Pro soon
$6/mo
  • Hosted encrypted sync across your machines
  • Durable history (survives log pruning)
  • Smart alerts (Slack/email/webhook)
  • Priority support & early access
Team soon
$12/seat
  • Everything in Pro
  • Aggregated team cost view
  • Attribution reports (per-dev/project/sprint)
  • Admin budgets & alert routing
  • SSO / SAML

Questions

Does my data leave my machine?

No. Burnmeter reads the session logs your agents already write locally (~/.claude, ~/.codex) and serves a dashboard on localhost. Nothing is uploaded. The optional Pro cross-device sync is opt-in and end-to-end encrypted — the relay only ever sees ciphertext.

Do I need an API key?

No. There is no API call to Anthropic or OpenAI. That's the whole point — for flat-fee Pro / Max plans there is no real-time usage API, so your local logs are the only accurate source of truth.

Which agents are supported?

Claude Code and Codex today — separately or combined in one view. The parser is pluggable, so more agents are on the roadmap.

Are the dollar figures exact?

They're best-effort estimates at published per-model pricing (Opus/Sonnet/Haiku, GPT-5.5/5.4/Codex/mini). On a flat-fee plan the real constraint is the rate limit — which Burnmeter tracks directly — so the $ is for relative insight: what's expensive, and how much cache saved you.

Is it really free?

The entire local dashboard is open source (AGPL-3.0) and free forever — every agent, every panel, never gated. Pro (~$6/mo) only adds services a single machine can't do alone: hosted multi-device sync, durable cross-device history, and smart alerts — and the sync relay is itself open-source and self-hostable for $0.