The Zombie Sentry

Stop paying for AI that isn't thinking. Reclaim GPU spend per your operator policy: alert, or — if you opt in — block in real time.

Forgotten notebooks. Runaway loops. Agents stuck firing the same kernel a thousand times a second while the bill clock runs. We watch the kernel-launch fingerprint of every PID through the eBPF ring buffer. When a process crosses your operator-set threshold, the outcome follows your policy: alert into the ledger, or — if you've armed enforcement — SIGKILL. Before any kill, three false-positive guards run (a multi-GPU NVML check, an in-window multi-GPU check, and a kernel-diversity check), each with its own audit counter; PID 0/1, the Sentry itself, and your protected PIDs are never killable. Your CFO gets the GPU-hours back, and every decision is recorded in the ledger for audit.