Agent Catalog
220+ specialized agents for your infrastructure. All agents use the same pricing: $0.50/GB after your first free GB.
High CPU, memory leaks, disk full, OOM kills, process crashes, network issues, boot failures, kernel panics.
High CPU, memory pressure, disk full, service failures, blue screens, event log errors, IIS issues.
OOMKill, restart loops, image pull failures, storage driver issues, network namespace problems.
Pod failures, scheduling issues, node problems, networking, ingress, rollout failures.
All pod/service issues within a specific namespace. Resource quota issues.
Node pressure conditions, kubelet issues, container runtime problems, kernel issues.
Cold start latency, timeout errors, memory limit hits, concurrency throttling.
Execution failures, scaling issues, binding errors, host health.
Execution errors, resource limits, deployment issues.
Task failures, service instability, load balancer health, capacity provider issues.
Service failures, node drain issues, overlay network problems.
VM/container failures, storage issues, cluster quorum, migration failures.
VM performance, storage latency, network issues, vMotion failures.
Instance failures, Nova scheduling, Neutron networking, Cinder storage.
GPU utilization issues, CUDA errors, memory overflow, driver problems, thermal throttling.
Thermal throttling, SD card wear, power issues, peripheral failures.
Hardware sensor alerts, RAID degradation, NIC failures, IPMI events.
Interruption patterns, capacity availability, failover behavior.
Job failures, queue bottlenecks, compute environment issues.
Slow queries, connection exhaustion, replication lag, lock contention, vacuum issues.
Slow queries, InnoDB buffer pool issues, replication lag, deadlocks.
Blocking chains, tempdb contention, query plan regression, Always On health.
Slow queries, replication lag, shard imbalances, connection storms.