CPU/Mem reactive · K8s default
Pod CPU/Memory
↓
threshold >70%
↓
Replica ±1 · ~30s
- ✕Usage ≠ performance
- ✕Reactive only
- ✕Manual tuning
Run Kubernetes
at peak performance for less
Wave is an integrated Kubernetes solution for scaling, sizing, traffic management, diagnostics, and node management. It addresses operational reliability challenges that Kubernetes platforms such as Amazon EKS and OpenShift do not cover.
Wave
Wave is a Kubernetes operations platform that automates autoscaling, resource sizing, incident diagnosis, and node provisioning in one integrated workflow.
THE PROBLEMSetup is done,
Setup is done,
but operations haven't even started.
Problems in K8s environments build up quietly. Unnoticed waste. Unexpected outages. Unfair traffic handling that erodes trust. Ultimately, the business bears the full cost.
Costs leaking out of sight
65% of containers use less than half of the CPU/memory they requested. You pay every month for resources you never use.
Scaling that breaks at every peak
Usage stays below the threshold, so HPA never moves. Pods only start scaling up after the sale has already begun.
Traffic that drags checkout down with it
K8s has no request priority. Under load, checkout requests are processed in the same order as simple reads.
HPA reacts to usage,
Autopilot learns performance
Autopilot scales pods with a performance model that learns the service's real behavior.
It decides in about 10 seconds, roughly 2× faster than HPA, with stability guardrails built in.
Autopilot
Autopilot Scheduler
Min/Max recommendations
Monitor Only
Workload-aware · ML model
latency · throughput
↓
ML auto-decision
↓
accurate · ~10s
- ✓Performance model
- ✓~2× faster than HPA
- ✓No threshold tuning
Pod requests, exactly right — fewer nodes
Wave Sizing learns each workload's real demand and recommends CPU and memory requests.
Keep burst headroom while unused requests disappear, and nodes and cost shrink together.
Smart Sizing
Real-time resizing
Smart Sizing report
Without Smart Sizing
With Smart Sizing
Free
Free
Free
Free
Free
Free
oversizedright-sizedfreed
Karpenter, faster,
Spot, safer
Node Warmup brings nodes up ahead of demand to remove cold-start waits, and Spot Placement guarantees a minimum number of on-demand nodes per workload before sending anything beyond that to Spot. A single dashboard shows nodes, Spot mix, and cost in one view.
Karpenter dashboard
Node Warmup
Spot Placement
K8S SCHEDULING PIPELINE→→Wave
Pod Created
Pending · awaiting Karpenter provisioning
(+30~90s)
Scheduled
ready✓
Node Warmup
Pre-provisions nodes ahead of demand — No waiting for node provisioning
RESULT
~70%↓
node costDashboards show metrics,
Diagnosis points to the cause
It continuously analyzes memory leaks, pod/container failures, pod scheduling delays, and idle nodes to surface risk before the alarm ever fires.
Memory leak
Pod/Container failure
Pod scheduling delay
Idle node
Grafana shows metrics. People still guess what went wrong.
ML-driven forecasting, detection, analysis.
No guessing. It's already on the list. ✓
As load rises,
cut from the lowest tier first
Four-tier priority-based traffic shaping on top of Istio handles critical traffic first and progressively throttles the rest as load rises. A spike in one service is contained before it becomes a broader outage.
Wave Flow
Without Wave Flow · Istio default→
→
Istio
no priority
✗✗✗✗✗
Checkout ~30%
DROP ✗
With Wave Flow · priority shaping→
→
CRITICAL
IMPORTANT
MODERATE
BULK
CRITICAL PROTECTED
Checkout 100% ✓
PVs before they fill up,
the unused surfaced
It forecasts capacity, expands volumes before pods stall, and reclaims unused PVs. Zero manual operations.
PVC auto-expansion
Capacity forecast
Unused PV detection
PERSISTENT VOLUMES · 4
USED
Wave Action
data-postgres-0
87%
+ AUTO-EXPAND ✓
redis-cache
22%
FORECAST · 7d
logs-archive
0%
→ CLEANUP
(Released · No PVC)
(Released · No PVC)
backup-vol
45%
healthy
Config as code,
results in Slack
Declare every feature as a CR and keep it in Git — GitOps-managed with no console drift. Every endpoint is published as an OpenAPI spec so you can auto-generate clients, and results arrive via Slack and webhooks.
CRD
OpenAPI
Alerts
apiVersion: wavek8s.com/v1alpha1 kind: WaveAutopilotPolicy metadata: name: web-autopilot spec: minReplicas: 2 mode: simulation
POST /v1/clusters "autopilot": true "min": 2 "max": 20 200 OK ✓
Config (in)Notify (out)
Git → CR apply
API client(OpenAPI)
Wave
# Slack
> Webhook
Frequently Asked Questions
Common questions before getting started. Reach out anytime to learn more.
Wave is a Kubernetes operations platform that integrates and manages Kubernetes scaling, resource sizing, incident diagnosis, traffic control, node provisioning, and more. Wave is not a simple autoscaling tool; through features such as Autoscale, Sizing, Diagnosis, Flow, Karpenter, and GPU, it manages the performance, cost, and stability issues that arise in Kubernetes operations.
The fastest way to try it.
Test and deploy the way you want, with no changes to your service environment.