Open source · Fleet-wide AIOps for Kubernetes

From Kubernetes alert to automated remediation.

Kubernaut detects signals, investigates root causes with an LLM-powered agent, selects a remediation workflow, and executes the fix — on a single cluster or across your entire fleet — or escalates to a human with a full RCA when it can’t.

Root cause found and a fix selected in under 3 minutes on average, while humans stay in control through approval gates and audit trails.

Scroll

How it works

A CRD-native remediation pipeline.

Six phases, one Remediation Orchestrator, and full audit trails from the first signal to the final notification.

Every remediation starts one of two ways: autonomously, the moment a signal fires from AlertManager or a Kubernetes Event, or interactively, when an operator opens a live investigation, watches it unfold in real time, and decides whether the recommended fix runs — more on that below. Either way, it’s the same pipeline from here.

  1. 01

    Signal Processing

    A dedicated controller enriches the signal with Kubernetes context (owner chain, namespace labels), then classifies environment, priority, and severity via Rego policy.

  2. 02

    AI Analysis

    The Kubernaut Agent investigates with 36 built-in tools — or, for a fleet-managed cluster, the byte-identical tool schema served by that cluster’s K8s MCP Server — produces a root cause analysis, and selects a workflow from the RemediationWorkflow catalog.

  3. 03

    Approval

    Low-risk actions auto-approve via OPA/Rego policy and confidence thresholds; higher-risk remediations notify an operator via Slack, Teams, or PagerDuty.

  4. 04

    Execution

    Fixes run as Kubernetes Jobs, Tekton Pipelines, or Ansible (AWX/AAP) — each under a dedicated ServiceAccount with short-lived, no-standing-privilege tokens.

  5. 05

    Effectiveness

    Post-remediation verification confirms alert resolution, checks for spec drift, and produces a four-dimensional health score.

  6. 06

    Notification

    Multi-channel delivery to Slack, PagerDuty, Teams, or log/file, with circuit-breaker retry and a full audit trail per attempt.

Analysis and fix selection are the fast part — about 3 minutes on average across the incidents below. Most of what’s left is deliberate: a 5-minute stabilization window before Effectiveness even starts scoring, so Kubernaut isn’t judging a cluster that hasn’t settled yet. End to end, signal to a verified fix, typically completes in under 12 minutes — no human required in the loop, for the cases that don’t need one.

Kubernaut Console

Not just autonomous — talk to it.

Every investigation is also a live conversation. The same agent that runs autonomously the moment a signal fires is reachable directly, too — open the Console over MCP or A2A, start a fresh investigation or join one already running, and watch it think in real time, with the same approval gates.

Recorded live: the Console investigating a real KubePodCrashLooping incident, discovering a workflow, and ruling out an in-cluster patch because the cluster is GitOps-managed. Loops like this typically close end to end — including Kubernaut’s own built-in wait before it verifies the fix — in under 12 minutes.

Live thinking panel

Watch the agent’s reasoning, tool calls, and investigation events stream in as they happen — not a spinner, the actual chain of thought.

RCA cards, not walls of text

Root cause arrives as a structured card: causal chain, confidence score, severity, and tool call count.

Workflow selection with alignment verdicts

Review the recommended remediation workflow and its parameters, with a countdown confirmation before anything runs.

Approval gate, built in

Approve, decline, or escalate with a reason — directly from the same conversation, no context switch to a separate tool.

Real incidents

See what the agent actually found.

No cherry-picked screenshots — every signal, root cause, and outcome below is captured verbatim from a real incident run.

IstioHighDenyRate Remediated 3m 57s 97% confidence

Every request in the namespace returning 403

Root cause

An Istio AuthorizationPolicy with an empty deny rule is silently blocking every request in the namespace.

Fix

Corrected the AuthorizationPolicy scope, restoring traffic without touching the app.

Try this scenario yourself

EtcdHighFragmentationRatio Remediated 2m 55s 97% confidence

All three etcd members at ~99.97% fragmentation

Root cause

Compaction had run but defragmentation never had — leaving ~62 MiB of dead BoltDB pages across all three etcd members, live data down to 16 KiB.

Fix

Sequential etcdctl defrag across all three members — followers first, then leader — with health checks between each.

Try this scenario yourself

KubePodCrashLooping Remediated 2m 17s 95% confidence

web-frontend crash-looping after an ArgoCD sync

Root cause

A bad commit synced by ArgoCD’s self-heal loop keeps re-breaking the ConfigMap — patching the cluster directly would be undone within seconds.

Fix

Selected a git-revert workflow instead of an in-cluster patch, so the fix survives the next sync.

Try this scenario yourself

PVRunwayShort Remediated 2m 53s 85% confidence

predict_linear projects this PVC exhausting in under an hour

Root cause

A sidecar container was writing ~400 MiB/hour of uncompressed data into a 512Mi PVC with no retention policy — caught by trend prediction before the volume filled.

Fix

Expanded the PVC online via its CSI driver, buying time before PostgreSQL would have crashed, while the underlying write-rate and retention issue gets fixed separately.

Try this scenario yourself

KubePodCrashLooping Remediated 2m 43s 93% confidence

api-gateway crash-looping — but the alert fired in the wrong namespace

Root cause

A bad directive in the postgres-config ConfigMap, two namespaces away, crashed Postgres — which cascaded into api-gateway and payment-processor, both crash-looping on a database they couldn’t reach.

Fix

Removed the bad directive from the ConfigMap and restarted the affected Deployment, instead of stopping at the symptom in the alerting namespace.

Try this scenario yourself

OperatorCSVFailed Remediated 4m 15s 92% confidence

The etcd operator’s CSV vanished entirely — OLM couldn’t resolve the package

Root cause

The etcd Subscription was patched to reference a CatalogSource that no longer existed, leaving OLM unable to resolve the operator — its ClusterServiceVersion was completely absent from the namespace.

Fix

Deleted and recreated the Subscription CRD against the correct CatalogSource, restoring the operator’s CSV.

Try this scenario yourself

Real signals, root-cause analyses, and outcomes captured verbatim from Kubernaut’s open demo scenario suite. The remediation workflows shown are reference examples — every deployment authors its own workflow catalog so fixes match your organization’s SOPs, tooling, and change-management process.

Fleet Management

One remediation brain for hundreds of clusters.

At hundreds of clusters, provisioning is already solved — your GitOps or fleet control plane handles that well. What doesn’t scale on its own is operations: every cluster still means its own on-call triage, its own root-cause digging, its own runbook sprawl. Fleet Management plugs into the estate you already run and extends one Kubernaut deployment across every cluster, so incident response scales with your fleet instead of your headcount.

Control-plane agnostic by design
Running a GitOps-managed fleet with no central control plane at all? Kubernaut’s built-in Fleet Metadata Cache covers the same ground out of the box — nothing extra to stand up. Already run a fleet control plane instead? Kubernaut plugs straight into it — Red Hat ACM / Open Cluster Management is supported today, with adapters for SUSE Rancher, Karmada, and Clusterpedia on the roadmap.
Cross-cluster root cause analysis
Every cluster in the fleet exposes a standard K8s MCP Server behind an MCP Gateway (Envoy AI Gateway or Kuadrant — external infrastructure you deploy once, the same way you’d stand up Prometheus). The agent’s tool schema is byte-identical whether it’s inspecting the hub or cluster #247, so root-cause chains that span clusters stay traceable end to end.

Security, by construction

Read-only reasoning. Scoped, audited execution.

Every guarantee below holds even if the model gets something wrong — no standing credentials, no unbounded blast radius, no action without an audit trail.

Scope-gated by design

The agent that investigates is read-only everywhere it runs — a locked-down investigator role with no write access, ever. What it can even be pointed at is gated separately: only resources labeled Kubernaut-managed are ever admitted, checked at the ingress point before the agent is invoked — two independent gates, not one assumption. The default role ships narrow; granting it anything more is an explicit, separately-bound decision you make — and Kubernaut flags it as a privilege-escalation risk when you do — never a side effect of a normal install or upgrade.

Execution scoped to a ServiceAccount you control

Remediation itself runs as a Kubernetes Job or Tekton PipelineRun on the target cluster, under a ServiceAccount you provision and scope to that one workflow — not a shared, standing credential. That’s different from agents that draft their own remediation and RBAC per incident: whatever grants that RBAC still has to hold every permission it might ever hand out. Kubernaut’s operators define the workflow and its ServiceAccount ahead of time, through the same review as any other change, so the blast radius is fixed and audited before an incident happens — not computed by a model in the middle of one.

Credentials never reach the model

Every result from an MCP tool call the agent reads back — Secret data, ConfigMaps, pod details — passes through a credential-scrubbing pipeline covering two dozen-plus patterns for database URLs, API keys, and tokens before it ever reaches the LLM’s context, not just a blanket redaction of Secret objects by type. If that pipeline ever fails, Kubernaut withholds the tool result entirely rather than risk passing anything unsanitized through — the failure mode is losing a data point mid-investigation, not leaking a credential.

Built-in prompt-injection defense

A shadow agent — a second, independent model — reviews every tool result for injection attempts, then reviews the full investigation again as it moves into workflow discovery — a phase handled by its own, separately configurable model — to catch attacks spread thin across multiple steps. It’s opt-in and fails closed: anything that looks like it’s steering the investigation rather than informing it stops execution for a human to look, not a guess to run with. Already run a dedicated prompt-injection or LLM-guardrail product? This layers underneath it, not instead of it.

Key capabilities

Built for safe, auditable remediation.

Every capability below is designed around one rule: humans stay in control, and every action is explainable after the fact.

Dual-Mode Operation

Autonomous end-to-end remediation, or interactive sessions where operators guide the agent via MCP or A2A — both share the same approval gates and audit trails.

Multi-Source Signal Ingestion

Prometheus alerts (reactive and proactive) and Kubernetes events, deduplicated by fingerprint at the ingress point before entering the pipeline. ServiceNow incidents are on the roadmap as a third signal source.

AI-Powered Root Cause Analysis

The Kubernaut Agent uses LLM providers (Vertex AI, OpenAI, Anthropic, Bedrock, Ollama, and more) with native Kubernetes inspection tools.

Workflow Catalog

Searchable, declarative RemediationWorkflow CRDs matched by category and label with confidence scoring.

Flexible Execution

Kubernetes Jobs, Tekton Pipelines, or Ansible (AWX/AAP) — pick the engine that matches the remediation.

Trust Ladder

Start in dry-run — Kubernaut investigates and selects a workflow but executes nothing. Layer in human approval next, gated by Rego policy, confidence thresholds, and admission webhooks. Graduate individual workflows to full autonomy only once you trust the results, and roll back at any time.

SOC2 Alignment

Full audit trails with 7-year retention, CRD reconstruction from audit events, and operator attribution on every action.

Effectiveness Tracking

Four-dimensional post-remediation scoring feeds back into the agent, so it learns to avoid repeating failed remediations.

Alert remediation is the pillar live today. Threat Remediation (security signals from Falco, Trivy, OPA/Gatekeeper) and Cost Optimization (FinOps via Koku, Kubecost, and OpenCost) are early-stage proposals under exploration for future releases — see the open issues for where each stands.

Built on tools you already run

No new platform to adopt.

Kubernaut plugs into your existing Kubernetes, observability, and automation stack.

Platform & Execution

  • Kubernetes
  • Prometheus
  • OPA / Rego
  • Tekton Pipelines
  • Ansible (AWX/AAP)

LLM Providers

  • Vertex AI
  • OpenAI
  • Anthropic
  • Amazon Bedrock
  • Ollama

Ready to find root cause in minutes, not hours?