Agent Fleet Telemetry 5 Active

Real-time autonomous inference, token utilization & dispatch health

Updated: Just now
Turns Dispatched (24h)
1,428
↑ 14.2% vs yesterday
Inference Cache Hit
88.4%
↑ 3.1% prompt snapping
Avg Turn Latency
1.18s
~ steady (OpenRouter)
Token Burn Rate
$4.12
↓ 24% under budget
Turn Volume & Token Throughput
Hourly distribution over the last 12 hours
Turns Dispatched
Cache Hits
250 175 100 25 06:00 08:00 10:00 12:00 14:00 16:00
Fleet Nodes
Tailnet LXC & Apple Silicon workers
Agent Model Status
V
vega
opus-5 streaming
A
atlas
flash-4.1 idle
L
lyra
sonnet-5 compaction
R
rho
kimi-k3 idle
K
arlo
gemini-flash reading