Monitor. Diagnose. Optimize. Control. Report.The whole Kubernetes operations lifecycle.
Wave runs all five stages in one console. It analyzes your cluster every day, finds the root cause, recommends the right configuration, then applies it automatically — filling the operational gaps Amazon EKS and OpenShift leave open.
Kubernetes operations run in a loop. Wave covers all five stages in one console.
- 01
Monitor
See every cluster without stitching tools together.
Cluster and workload dashboards
- 02
Diagnose
Find the cause, not the symptom.
Memory Leak Detection · Container Failure Diagnosis · Pod Scheduling Delay Detection
- 03
Optimize
Cut waste and scale faster, without hand work.
Autopilot · Smart Sizing · Realtime Resizing
- 04
Control
Keep an optimized cluster inside its limits.
Autopilot Scheduler · Wave Flow
- 05
Report & Alert
Leave a record a person can act on.
Smart Sizing Report · failure evidence capture · Alerts
↻Report and Alert feeds the next Monitor. All five stages work from the same picture.
The features teams turn on first
Grouped by product area — from scaling to failure diagnosis.
Resource Optimization
Right-size, scale, and provision compute
K8s Diagnosis
Find and fix cluster health issues
Traffic Protection
Protect critical traffic under load
GPU Visibility & Virtualization
See every GPU on K8s, and share one card safely
Console Demo
See the console before you install anything
Click through sizing recommendations, Autopilot scaling, and K8s diagnosis — with simulated data, right in your browser.
Explore the console demo →What Wave reads, how it decides, what it changes.
The five stages above run on one mechanism. Wave collects metrics, logs and Kubernetes state together, reasons over them, and applies the result.
Reads
What Wave reads
- Pod & workload metrics
- K8s events & API state
- GPU telemetry
- PV / PVC usage
- Pod scheduling state
- Istio mesh telemetry
- + and more signals
Various cadences. Each loop ticks on its own schedule, from seconds to days.
Decides
How Wave decides
- Workload performance models (ML)
- Smart Sizing models (ML)
- Time-series forecasts (ML)
- Rule-based thresholds & cooldowns
- LLM + skillsNEW
- + and more brains
The right brain for the job. Now including LLMs for event-driven diagnosis.
Changes
What Wave changes
- Adjust replicas
- Resize CPU / memory requests
- Provision nodes
- Expand PVCs
- Shed traffic via Istio
- Recommend changes
- Narrate to Slack / page SRE
- + and more actions
Apply, recommend, or narrate, fitted to Wave's level of autonomy.
What problem are you facing?
Select your challenge — we'll show you exactly how Wave helps.
Cut Kubernetes cost
Stop overpaying for K8s resources you aren't using.
"65% of our containers use less than half their requested CPU and memory."
3 scenarios →Right-size requests & limits — safely
The #1 waste and OOMKill source, fixed without restarts.
"We finally trust automated resizing in prod."
3 scenarios →Fast, reliable autoscaling
Beat HPA's 30s–3min lag; survive spikes.
"Scaling decisions in ~10s, not minutes."
3 scenarios →Run Karpenter in production
Run Karpenter reliably — with visibility and spot savings.
"Karpenter is fast but we have no idea what it's actually doing or how much it's costing us."
3 scenarios →Stop incidents — OOMKills & CrashLoops
Catch failures before the 3am page.
"We see the incident coming now."
3 scenarios →Trusted by Leading Organizations
3 simple steps to production
Works on EKS, GKE, AKS, OpenShift, and self-managed Kubernetes 1.26+.
Request a license key
Free for clusters under 200 vCPUs. We email a license key and GHCR pull secret within one business day.
Request free key →Install via Helm
One values file with your key and storage class, one helm install. Air-gapped clusters supported.
$ helm repo add wave-autoscale-helm \ https://release.waveautoscale.io/helm-chart$ helm install wave-autoscale-helm \ wave-autoscale-helm/wave-autoscale-helm \ -f values-ghcr.yaml \ -n wave-autoscale --create-namespace
Open the console
Port-forward, sign in, and Wave starts auto-discovering workloads. Autopilot can run in observe-only mode first.
$ kubectl port-forward -n wave-autoscale \ svc/wave-autoscale-svc 3025:3025# open http://localhost:3025
Common questions, clear answers
We already use HPA — why do we need this?
HPA only watches whether resource usage crosses a threshold, not how your workload actually performs. Wave Autopilot uses ML-based workload performance modeling to reach scaling decisions in about 10 seconds — roughly 2× faster than HPA, without threshold tuning.
Isn't KEDA the same thing?
No. KEDA specializes in event-driven workloads (Kafka, queues) — a different objective. KEDA complements HPA and Wave Autopilot rather than replacing them. Wave Autopilot scales long-running services based on workload performance, which is a separate problem.
How is this different from VPA for resource sizing?
VPA uses CPU percentile statistics alone, so a fixed CPU allocation can't adapt to sporadic request surges. Wave Smart Sizing factors in both CPU percentiles and real-time workload demand, maintaining optimal success rates — for example allocating 2.0 cores instead of 1.5 when bursts demand it.
Does Wave Flow replace Istio?
No. Wave Flow runs on top of Istio — adding priority shaping, a virtual waiting room, and visibility through Envoy filters and control-plane extensions. Your existing Istio mesh is untouched; Wave Flow makes overload behavior graceful instead of treating every request equally.
We use Karpenter already. What does Wave Karpenter add?
Karpenter is fast but not production-ready out of the box — cold-start delays, limited visibility, and naive spot usage can hurt at scale. Wave Karpenter adds Node Warmup pre-provisioning, a unified monitoring dashboard, and workload-threshold-based safe spot placement — enabling ~70% node savings without disruption churn.
We already have Grafana — why Wave Diagnosis?
Grafana shows you the metrics, but you still have to guess what's wrong. Threshold alerts miss slowly-progressing issues until they become incidents. Wave Diagnosis ships with five ML diagnostics — cluster resource forecasting (7–60 days out), memory leak detection, CPU utilization analysis, pod scheduling delay detection, and idle node detection — so you can shift from reactive to proactive operations.
Will this work in our air-gapped or on-prem environment?
Yes. Wave runs entirely inside your cluster with no external dependencies. Air-gapped environments are fully supported, including private container registries. Wave is an AWS EKS Service Ready Partner and a Red Hat Certified Partner, and also runs on bare-metal Kubernetes.
Ready to operate Kubernetes the right way?
Start with a free Smart Sizing Report on your own cluster. No credit card. White-glove onboarding included.