# claude-gauge

Hardware instrument cluster displaying Claude Code session telemetry
in real time.

![Monitor-mounted cluster with four gauges and annunciator row](docs/images/monitor-dash.png)

Four analog needle gauges (5h fuel, tokens/min tach, thinking ratio,
cache hit) plus an annunciator row of model-indicator and warning
lamps, driven by an ESP32 polling a local Python daemon. The daemon
reads either Claude Code's native OpenTelemetry feed through a
Prometheus stack (architecture A) or `ccusage` CLI aggregates with a
direct JSONL tail for the tach (architecture B). Firmware and
cluster are identical across both.

Fighter-jet / race-car aesthetic. Physical-first: the deep stats
live in Grafana (A) or `ccusage` (B); the dial on the desk is the
ambient summary.

## Documentation

Full documentation is in the [wiki](https://forgejo.labbity.unbiasedgeek.com/archeious/claude-gauge/wiki):

* **Home** — overview and cluster at a glance
* **Architecture** — two-architecture tradeoff, daemon contract
* **DataSources** — Docker Compose + PromQL (A), `ccusage` +
  watchdog (B)
* **Hardware** — X27.168 steppers, ESP32 wiring, firmware,
  enclosure
* **Roadmap** — phases, shipped, deferred
* **Ideas** — exotic enclosure variants, metrics brainstorm,
  parked thoughts

Working notes live in [PLAN.md](PLAN.md). Session records and
in-flight thinking happen there; the wiki is the curated surface.

## Status

Scaffolded. Phase A pending architecture decision.