Instrument cluster and dashboard for Claude Code session telemetry.
Find a file
Jeff Smith fdab957b55 Add monitor-dash render to README; prepare wiki layout
- Move uploaded renders into docs/images/ (tracked).
- Insert the Monitor Dash render at the top of README.md as the
  headline image of the project.
- Rewrite README body to point at the forgejo wiki (six pages now
  live) as the canonical documentation surface, with PLAN.md
  staying as working notes.
- Gitignore docs/wiki/ so the wiki git checkout does not bleed
  into the main repo.

Refs #1

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-17 19:31:02 -06:00
docs/images Add monitor-dash render to README; prepare wiki layout 2026-04-17 19:31:02 -06:00
src/claude_gauge Initial scaffold 2026-04-17 19:01:30 -06:00
tests Initial scaffold 2026-04-17 19:01:30 -06:00
.gitignore Add monitor-dash render to README; prepare wiki layout 2026-04-17 19:31:02 -06:00
.python-version Initial scaffold 2026-04-17 19:01:30 -06:00
LICENSE Initial scaffold 2026-04-17 19:01:30 -06:00
PLAN.md Flesh out PLAN.md with two-architecture implementation detail 2026-04-17 19:18:59 -06:00
pyproject.toml Initial scaffold 2026-04-17 19:01:30 -06:00
README.md Add monitor-dash render to README; prepare wiki layout 2026-04-17 19:31:02 -06:00

claude-gauge

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

Monitor-mounted cluster with four gauges and annunciator row

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:

  • 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. Session records and in-flight thinking happen there; the wiki is the curated surface.

Status

Scaffolded. Phase A pending architecture decision.