runtimeloading

page_shellloading

fontsloading

diorama_sceneloading

ClusterMind Start using ClusterMind

AI SRE for Kubernetes you run yourself. It finds the root cause and waits for a person to approve the fix.

Start using ClusterMind

or scroll to play it: one incident, six steps

AI SRE for self-managed Kubernetes

Watch ClusterMind fix a broken node.

Scroll to play

worker-01

worker-02

worker-03

worker-03NotReady

postgres-0Terminating

pvc-7f3a9cattaching

since 02:14

ClusterMind agent read-only · no cluster-admin

Reading, 02:14 scheduled run node_health worker-03 NotReady statefulset_stuck_pods postgres-0 longhorn_stuck_volumes pvc-7f3a9c

#platform-incidents

#platform-incidents02:17

ClusterMind

postgres-0 is stranded on dead worker-03, so its Longhorn volume loops on attach. A healthy replica is on worker-02.

Proposed fix: force-delete db/postgres-0, then open a PR setting nodeDownPodDeletionPolicy.

@dana on call

Step 1 of 6

A quiet night on prod‑bm‑01

Three bare-metal workers. postgres‑0 runs on worker‑03 with a Longhorn volume. ClusterMind runs its checks on a schedule and changes nothing.

Scroll

Built for the Kubernetes clusters cloud tools forgot.

Deep diagnostics for bare metal, k3s, RKE2 and Talos. ClusterMind understands Longhorn failures, stranded StatefulSets and ArgoCD drift, then turns the fix into a reviewed GitOps PR.

Start using ClusterMind Walk through the incident

Incident on prod-bm-01Criticalworker-03 NotReady

02:14

Scheduled run finds 3 critical issuesnode_health · statefulset_stuck_pods · longhorn_stuck_volumes

02:16

One causepostgres-0 is stranded on dead worker-03, so its Longhorn volume loops on attach.

02:17

Proposed fix, waiting on a personForce-delete db/postgres-0, then open a PR setting nodeDownPodDeletionPolicy.Checked first: a healthy Longhorn replica is on worker-02.

02:20

Pull request openedOpens after approval

02:23

Checks re-runWaiting

Nine minutes of one night, slowed down.

The same incident, stage by stage. A worker dies at 2 a.m. with a database on it. This is what ClusterMind did, and where it stopped to ask.

Investigate · prod-bm-01 · 02:14

Three critical findings from one scheduled run.

Deep diagnostics run every 6 hours by default, or on request. Read-only.

read-only agent

checkresult

node_healthworker-03 NotReady

statefulset_stuck_podspostgres-0 Terminating

longhorn_stuck_volumespvc-7f3a9c attaching

argocd_sync_statusok

Built for the stack you actually run.

Distributions

bare metalk3sRKE2Taloskubeadm

Around them

LonghornArgoCDPrometheusAlertmanagerSlack

Managed-cloud SRE tools know EKS. ClusterMind knows what happens when Longhorn won't attach after a node dies.

01 Longhorn attach-deadlock loops critical
longhorn_stuck_volumes
longhorn_instance_managers

02 StatefulSet pods stranded on dead nodes critical
statefulset_stuck_pods

03 Nodes left cordoned after an upgrade critical
node_health
node_conditions

04 ArgoCD drift after a hand fix in production medium
argocd_sync_status

Built from real production incidents, not generic troubleshooting prompts.

Each check carries the incident that produced it and the safe next step. 21 checks, 9 of them for self-managed stacks. Deep diagnostics run every 6 hours by default, or on request in any thread.

- name: statefulset_stuck_pods
  description: StatefulSet pods stuck on failed nodes
  severity: critical
  context: |
    Incident ref: PostgreSQL stuck on a dead node for hours
    StatefulSet pods do NOT auto-reschedule.
    Check if data loss is acceptable before force-deleting.

Every fix is reviewable before it ships.

ClusterMind never holds cluster-admin. Two agents with different permissions, and a person between them. No autonomous destructive actions.

On its ownread-only agent

Run scheduled and on-demand checks

Correlate nodes, volumes, pods and sync state

Explain the cause and propose a specific change

Only after a person approvesprivileged agent

Execute the approved change, scoped to one cluster

Open a pull request in your GitOps repo

Re-run the checks and post the result

Know where your cluster data goes.

Raw cluster data goes only to Anthropic, under your key. ClusterMind stores incident records and the agent's write-ups. Those can quote log lines. Connected Slack and GitHub integrations also receive information. The control plane holds your workspace Anthropic key when one is set; RBAC determines what the agent can read, with no redaction step.

Logs, specs, events, secrets

Your environment: Read here
Anthropic API, your key: Yes, as agent output
ClusterMind: May appear in stored evidence and write-ups

Prompts and inference

Your environment: Sent from here
Anthropic API, your key: Yes, billed to you
ClusterMind: Never

Incidents, write-ups, approvals, evidence, usage

Your environment: Created here
Anthropic API, your key: No
ClusterMind: Yes

Keep Prometheus. Keep Alertmanager.

Alerting tells you something is wrong. ClusterMind works out why and proposes the fix. It doesn't try to page you faster.

Could you build this with Claude + kubectl? Yes.

Then you'd also own all of this:

SafetyRBAC boundariesApproval flowMulti-cluster safetyVerification

PlumbingCurated checksGitOps remediationSlack workflowUsage and cost tracking

Built for teams who run their own Kubernetes.

For

Bare metal, k3s, RKE2, Talos and kubeadm clusters

Longhorn for storage, ArgoCD for GitOps

1–10 person platform teams: on-prem, edge, data center, sovereign, homelab-to-production

Teams already running Prometheus and Alertmanager

Not for

Managed-cloud fleets on EKS, GKE or AKS. Cloud-native agents already serve them.

Sub-minute autonomous detection

Remediation with no human approval

Run Kubernetes your way. Keep control of every fix.

Start using ClusterMind Read-only until someone approves. Review how cluster data is processed in our Privacy Policy.

ClusterMind Start using ClusterMind

AI SRE for Kubernetes you run yourself. It finds the root cause and waits for a person to approve the fix.

Start using ClusterMind

or scroll to play it: one incident, six steps

AI SRE for self-managed Kubernetes

Watch ClusterMind fix a broken node.

Scroll to play

worker-01

worker-02

worker-03

worker-03NotReady

postgres-0Terminating

pvc-7f3a9cattaching

since 02:14

ClusterMind agent read-only · no cluster-admin

Reading, 02:14 scheduled run node_health worker-03 NotReady statefulset_stuck_pods postgres-0 longhorn_stuck_volumes pvc-7f3a9c

#platform-incidents

#platform-incidents02:17

ClusterMind

postgres-0 is stranded on dead worker-03, so its Longhorn volume loops on attach. A healthy replica is on worker-02.

Proposed fix: force-delete db/postgres-0, then open a PR setting nodeDownPodDeletionPolicy.

@dana on call

Step 1 of 6

A quiet night on prod‑bm‑01

Three bare-metal workers. postgres‑0 runs on worker‑03 with a Longhorn volume. ClusterMind runs its checks on a schedule and changes nothing.

Scroll

Built for the Kubernetes clusters cloud tools forgot.

Deep diagnostics for bare metal, k3s, RKE2 and Talos. ClusterMind understands Longhorn failures, stranded StatefulSets and ArgoCD drift, then turns the fix into a reviewed GitOps PR.

Start using ClusterMind Walk through the incident

Incident on prod-bm-01Criticalworker-03 NotReady

02:14

Scheduled run finds 3 critical issuesnode_health · statefulset_stuck_pods · longhorn_stuck_volumes

02:16

One causepostgres-0 is stranded on dead worker-03, so its Longhorn volume loops on attach.

02:17

Proposed fix, waiting on a personForce-delete db/postgres-0, then open a PR setting nodeDownPodDeletionPolicy.Checked first: a healthy Longhorn replica is on worker-02.

02:20

Pull request openedOpens after approval

02:23

Checks re-runWaiting

Nine minutes of one night, slowed down.

The same incident, stage by stage. A worker dies at 2 a.m. with a database on it. This is what ClusterMind did, and where it stopped to ask.

prod-bm-01 · 02:14

Three critical findings from one scheduled run.

Deep diagnostics run every 6 hours by default, or on request. Read-only.

read-only agent

checkresult

node_healthworker-03 NotReady

statefulset_stuck_podspostgres-0 Terminating

longhorn_stuck_volumespvc-7f3a9c attaching

argocd_sync_statusok

Built for the stack you actually run.

Distributions

bare metalk3sRKE2Taloskubeadm

Around them

LonghornArgoCDPrometheusAlertmanagerSlack

Managed-cloud SRE tools know EKS. ClusterMind knows what happens when Longhorn won't attach after a node dies.

01 Longhorn attach-deadlock loops critical
longhorn_stuck_volumes
longhorn_instance_managers

02 StatefulSet pods stranded on dead nodes critical
statefulset_stuck_pods

03 Nodes left cordoned after an upgrade critical
node_health
node_conditions

04 ArgoCD drift after a hand fix in production medium
argocd_sync_status

Built from real production incidents, not generic troubleshooting prompts.

Each check carries the incident that produced it and the safe next step. 21 checks, 9 of them for self-managed stacks. Deep diagnostics run every 6 hours by default, or on request in any thread.

- name: statefulset_stuck_pods
  description: StatefulSet pods stuck on failed nodes
  severity: critical
  context: |
    Incident ref: PostgreSQL stuck on a dead node for hours
    StatefulSet pods do NOT auto-reschedule.
    Check if data loss is acceptable before force-deleting.

Every fix is reviewable before it ships.

ClusterMind never holds cluster-admin. Two agents with different permissions, and a person between them. No autonomous destructive actions.

On its ownread-only agent

Run scheduled and on-demand checks

Correlate nodes, volumes, pods and sync state

Explain the cause and propose a specific change

Only after a person approvesprivileged agent

Execute the approved change, scoped to one cluster

Open a pull request in your GitOps repo

Re-run the checks and post the result

Know where your cluster data goes.

Raw cluster data goes only to Anthropic, under your key. ClusterMind stores incident records and the agent's write-ups. Those can quote log lines. Connected Slack and GitHub integrations also receive information. The control plane holds your workspace Anthropic key when one is set; RBAC determines what the agent can read, with no redaction step.

Where each kind of data goes
What	Your environment	Anthropic API, your key	ClusterMind
Logs, specs, events, secrets	Read here	Yes, as agent output	May appear in stored evidence and write-ups
Prompts and inference	Sent from here	Yes, billed to you	Never
Incidents, write-ups, approvals, evidence, usage	Created here	No	Yes

Keep Prometheus. Keep Alertmanager.

Alerting tells you something is wrong. ClusterMind works out why and proposes the fix. It doesn't try to page you faster.

Could you build this with Claude + kubectl? Yes.

Then you'd also own all of this:

SafetyRBAC boundariesApproval flowMulti-cluster safetyVerification

PlumbingCurated checksGitOps remediationSlack workflowUsage and cost tracking

Built for teams who run their own Kubernetes.

For

Bare metal, k3s, RKE2, Talos and kubeadm clusters

Longhorn for storage, ArgoCD for GitOps

1–10 person platform teams: on-prem, edge, data center, sovereign, homelab-to-production

Teams already running Prometheus and Alertmanager

Not for

Managed-cloud fleets on EKS, GKE or AKS. Cloud-native agents already serve them.

Sub-minute autonomous detection

Remediation with no human approval

Run Kubernetes your way. Keep control of every fix.

Start using ClusterMind Read-only until someone approves. Review how cluster data is processed in our Privacy Policy.