Real-time Kubernetes dashboard for SREs — live cluster state, drain wizard, YAML editor, just-in-time exec access, cost analysis, and AI diagnosis in a single binary
Route the easy work your expensive Claude model keeps repeating down to haiku/sonnet — post-hoc session analysis, no realtime router, no extra LLM calls.
Finds the metrics nobody ever asks to dance. Audits Prometheus/Mimir against Grafana usage, ranks waste by cardinality and cost, generates drop rules, gates CI.