Merge pull request #2360 from OneUptime/k8s-impl

feat: Add Kubernetes Cluster Management and Monitoring Agent
2026-04-06 00:32:12 +02:00 · 2026-03-18 18:54:29 +00:00
parent 5e15bf1bdc e8fe9a0f0d
commit 0e0829bdd7
107 changed files with 7523 additions and 376 deletions
--- a/HelmChart/Public/kubernetes-agent/.helmignore
+++ b/HelmChart/Public/kubernetes-agent/.helmignore
@@ -0,0 +1,18 @@
+# Patterns to ignore when building packages.
+.DS_Store
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+.project
+.idea/
+*.tmproj
+.vscode/
--- a/HelmChart/Public/kubernetes-agent/Chart.yaml
+++ b/HelmChart/Public/kubernetes-agent/Chart.yaml
@@ -0,0 +1,15 @@
+apiVersion: v2
+name: kubernetes-agent
+description: OneUptime Kubernetes Monitoring Agent — collects cluster metrics, events, and logs via OpenTelemetry and sends them to your OneUptime instance.
+icon: https://raw.githubusercontent.com/OneUptime/oneuptime/master/Home/Static/img/OneUptimePNG/1.png
+
+type: application
+
+version: 0.1.0
+
+appVersion: "1.0.0"
+
+annotations:
+  artifacthub.io/license: MIT
+  artifacthub.io/category: monitoring-logging
+  artifacthub.io/prerelease: "false"
--- a/HelmChart/Public/kubernetes-agent/templates/NOTES.txt
+++ b/HelmChart/Public/kubernetes-agent/templates/NOTES.txt
@@ -0,0 +1,24 @@
+OneUptime Kubernetes Agent has been installed.
+
+Cluster Name: {{ .Values.clusterName }}
+OneUptime URL: {{ .Values.oneuptime.url }}
+
+The agent is now collecting:
+  - Node, pod, and container resource metrics (kubeletstats)
+  - Cluster-level metrics: deployments, replicas, pod phases (k8s_cluster)
+  - Kubernetes events (k8sobjects)
+{{- if .Values.controlPlane.enabled }}
+  - Control plane metrics: etcd, API server, scheduler, controller manager (prometheus)
+{{- end }}
+{{- if .Values.logs.enabled }}
+  - Pod logs from /var/log/pods (filelog DaemonSet)
+{{- end }}
+
+To verify the agent is running:
+  kubectl get pods -n {{ .Release.Namespace }} -l app.kubernetes.io/name={{ include "kubernetes-agent.name" . }}
+
+To check collector logs:
+  kubectl logs -n {{ .Release.Namespace }} -l app.kubernetes.io/name={{ include "kubernetes-agent.name" . }} -c otel-collector
+
+Your cluster should appear in OneUptime within a few minutes at:
+  {{ .Values.oneuptime.url }}/dashboard/<project-id>/kubernetes
--- a/HelmChart/Public/kubernetes-agent/templates/_helpers.tpl
+++ b/HelmChart/Public/kubernetes-agent/templates/_helpers.tpl
@@ -0,0 +1,59 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "kubernetes-agent.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+*/}}
+{{- define "kubernetes-agent.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "kubernetes-agent.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "kubernetes-agent.labels" -}}
+helm.sh/chart: {{ include "kubernetes-agent.chart" . }}
+{{ include "kubernetes-agent.selectorLabels" . }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+app.kubernetes.io/part-of: oneuptime
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "kubernetes-agent.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "kubernetes-agent.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Service account name
+*/}}
+{{- define "kubernetes-agent.serviceAccountName" -}}
+{{- if .Values.serviceAccount.name }}
+{{- .Values.serviceAccount.name }}
+{{- else }}
+{{- include "kubernetes-agent.fullname" . }}
+{{- end }}
+{{- end }}
--- a/HelmChart/Public/kubernetes-agent/templates/configmap-daemonset.yaml
+++ b/HelmChart/Public/kubernetes-agent/templates/configmap-daemonset.yaml
@@ -0,0 +1,140 @@
+{{- if .Values.logs.enabled }}
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "kubernetes-agent.fullname" . }}-daemonset
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "kubernetes-agent.labels" . | nindent 4 }}
+data:
+  otel-collector-config.yaml: |
+    extensions:
+      health_check:
+        endpoint: "0.0.0.0:13133"
+
+    receivers:
+      # Collect pod logs from /var/log/pods
+      filelog:
+        include:
+          - /var/log/pods/*/*/*.log
+        exclude:
+          # Exclude the agent's own logs to avoid feedback loop
+          - /var/log/pods/{{ "{{ .Release.Namespace }}" }}_{{ "{{ include \"kubernetes-agent.fullname\" . }}" }}*/**/*.log
+        start_at: end
+        include_file_path: true
+        include_file_name: false
+        operators:
+          # Parse CRI log format
+          - type: router
+            id: get-format
+            routes:
+              - output: parser-docker
+                expr: 'body matches "^\\{"'
+              - output: parser-cri
+                expr: 'body matches "^[^ Z]+ "'
+              - output: parser-containerd
+                expr: 'body matches "^[^ Z]+Z"'
+          # Docker JSON log format
+          - type: json_parser
+            id: parser-docker
+            output: extract-metadata-from-filepath
+            timestamp:
+              parse_from: attributes.time
+              layout: '%Y-%m-%dT%H:%M:%S.%LZ'
+          # CRI log format
+          - type: regex_parser
+            id: parser-cri
+            regex: '^(?P<time>[^ Z]+) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$'
+            output: extract-metadata-from-filepath
+            timestamp:
+              parse_from: attributes.time
+              layout: '%Y-%m-%dT%H:%M:%S.%L%j'
+          # Containerd log format
+          - type: regex_parser
+            id: parser-containerd
+            regex: '^(?P<time>[^ ^Z]+Z) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$'
+            output: extract-metadata-from-filepath
+            timestamp:
+              parse_from: attributes.time
+              layout: '%Y-%m-%dT%H:%M:%S.%LZ'
+          # Extract k8s metadata from file path
+          - type: regex_parser
+            id: extract-metadata-from-filepath
+            regex: '^.*\/(?P<namespace>[^_]+)_(?P<pod_name>[^_]+)_(?P<uid>[a-f0-9\-]+)\/(?P<container_name>[^\._]+)\/(?P<restart_count>\d+)\.log$'
+            parse_from: attributes["log.file.path"]
+          - type: move
+            from: attributes.log
+            to: body
+          - type: move
+            from: attributes.stream
+            to: attributes["log.iostream"]
+          - type: move
+            from: attributes.namespace
+            to: resource["k8s.namespace.name"]
+          - type: move
+            from: attributes.pod_name
+            to: resource["k8s.pod.name"]
+          - type: move
+            from: attributes.container_name
+            to: resource["k8s.container.name"]
+          - type: move
+            from: attributes.uid
+            to: resource["k8s.pod.uid"]
+
+    processors:
+      # Enrich with K8s metadata
+      k8sattributes:
+        auth_type: serviceAccount
+        extract:
+          metadata:
+            - k8s.pod.name
+            - k8s.pod.uid
+            - k8s.namespace.name
+            - k8s.node.name
+            - k8s.deployment.name
+            - k8s.replicaset.name
+            - k8s.statefulset.name
+            - k8s.daemonset.name
+            - k8s.container.name
+        pod_association:
+          - sources:
+              - from: resource_attribute
+                name: k8s.pod.uid
+
+      # Stamp with cluster name
+      resource:
+        attributes:
+          - key: k8s.cluster.name
+            value: {{ .Values.clusterName | quote }}
+            action: upsert
+
+      batch:
+        send_batch_size: 1024
+        timeout: 10s
+
+      memory_limiter:
+        check_interval: 5s
+        limit_mib: 200
+        spike_limit_mib: 50
+
+    exporters:
+      otlphttp:
+        endpoint: "{{ .Values.oneuptime.url }}/otlp"
+        headers:
+          x-oneuptime-token: "${env:ONEUPTIME_API_KEY}"
+
+    service:
+      extensions:
+        - health_check
+      pipelines:
+        logs:
+          receivers:
+            - filelog
+          processors:
+            - memory_limiter
+            - k8sattributes
+            - resource
+            - batch
+          exporters:
+            - otlphttp
+{{- end }}
--- a/HelmChart/Public/kubernetes-agent/templates/configmap-deployment.yaml
+++ b/HelmChart/Public/kubernetes-agent/templates/configmap-deployment.yaml
@@ -0,0 +1,183 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "kubernetes-agent.fullname" . }}-deployment
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "kubernetes-agent.labels" . | nindent 4 }}
+data:
+  otel-collector-config.yaml: |
+    extensions:
+      health_check:
+        endpoint: "0.0.0.0:13133"
+
+    receivers:
+      # Collect node, pod, and container resource metrics from kubelet
+      kubeletstats:
+        collection_interval: {{ .Values.collectionInterval }}
+        auth_type: serviceAccount
+        endpoint: "https://${env:NODE_NAME}:10250"
+        insecure_skip_verify: true
+        metric_groups:
+          - node
+          - pod
+          - container
+        extra_metadata_labels:
+          - container.id
+        k8s_api_config:
+          auth_type: serviceAccount
+
+      # Collect cluster-level metrics from the Kubernetes API
+      k8s_cluster:
+        collection_interval: {{ .Values.collectionInterval }}
+        node_conditions_to_report:
+          - Ready
+          - MemoryPressure
+          - DiskPressure
+          - PIDPressure
+          - NetworkUnavailable
+        allocatable_types_to_report:
+          - cpu
+          - memory
+          - storage
+
+      # Watch Kubernetes events and ingest as logs
+      k8sobjects:
+        objects:
+          - name: events
+            mode: watch
+            group: events.k8s.io
+
+      {{- if .Values.controlPlane.enabled }}
+      # Scrape control plane metrics via Prometheus endpoints
+      prometheus:
+        config:
+          scrape_configs:
+            - job_name: etcd
+              scheme: https
+              tls_config:
+                insecure_skip_verify: {{ .Values.controlPlane.etcd.insecureSkipVerify }}
+              static_configs:
+                {{- range .Values.controlPlane.etcd.endpoints }}
+                - targets:
+                    - {{ . | quote }}
+                {{- end }}
+            - job_name: kube-apiserver
+              scheme: https
+              tls_config:
+                insecure_skip_verify: {{ .Values.controlPlane.apiServer.insecureSkipVerify }}
+              bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+              static_configs:
+                {{- range .Values.controlPlane.apiServer.endpoints }}
+                - targets:
+                    - {{ . | quote }}
+                {{- end }}
+            - job_name: kube-scheduler
+              scheme: https
+              tls_config:
+                insecure_skip_verify: {{ .Values.controlPlane.scheduler.insecureSkipVerify }}
+              bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+              static_configs:
+                {{- range .Values.controlPlane.scheduler.endpoints }}
+                - targets:
+                    - {{ . | quote }}
+                {{- end }}
+            - job_name: kube-controller-manager
+              scheme: https
+              tls_config:
+                insecure_skip_verify: {{ .Values.controlPlane.controllerManager.insecureSkipVerify }}
+              bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+              static_configs:
+                {{- range .Values.controlPlane.controllerManager.endpoints }}
+                - targets:
+                    - {{ . | quote }}
+                {{- end }}
+      {{- end }}
+
+    processors:
+      # Enrich all telemetry with Kubernetes metadata
+      k8sattributes:
+        auth_type: serviceAccount
+        extract:
+          metadata:
+            - k8s.pod.name
+            - k8s.pod.uid
+            - k8s.namespace.name
+            - k8s.node.name
+            - k8s.deployment.name
+            - k8s.replicaset.name
+            - k8s.statefulset.name
+            - k8s.daemonset.name
+            - k8s.job.name
+            - k8s.cronjob.name
+            - k8s.container.name
+          labels:
+            - tag_name: k8s.pod.label.app
+              key: app
+              from: pod
+            - tag_name: k8s.pod.label.app.kubernetes.io/name
+              key: app.kubernetes.io/name
+              from: pod
+        pod_association:
+          - sources:
+              - from: resource_attribute
+                name: k8s.pod.ip
+          - sources:
+              - from: resource_attribute
+                name: k8s.pod.uid
+          - sources:
+              - from: connection
+
+      # Stamp all telemetry with the cluster name
+      resource:
+        attributes:
+          - key: k8s.cluster.name
+            value: {{ .Values.clusterName | quote }}
+            action: upsert
+
+      # Batch telemetry for efficient export
+      batch:
+        send_batch_size: 200
+        send_batch_max_size: 500
+        timeout: 10s
+
+      # Limit memory usage
+      memory_limiter:
+        check_interval: 5s
+        limit_mib: 1500
+        spike_limit_mib: 300
+
+    exporters:
+      otlphttp:
+        endpoint: "{{ .Values.oneuptime.url }}/otlp"
+        headers:
+          x-oneuptime-token: "${env:ONEUPTIME_API_KEY}"
+
+    service:
+      extensions:
+        - health_check
+      pipelines:
+        metrics:
+          receivers:
+            - kubeletstats
+            - k8s_cluster
+            {{- if .Values.controlPlane.enabled }}
+            - prometheus
+            {{- end }}
+          processors:
+            - memory_limiter
+            - k8sattributes
+            - resource
+            - batch
+          exporters:
+            - otlphttp
+        logs:
+          receivers:
+            - k8sobjects
+          processors:
+            - memory_limiter
+            - k8sattributes
+            - resource
+            - batch
+          exporters:
+            - otlphttp
--- a/HelmChart/Public/kubernetes-agent/templates/daemonset.yaml
+++ b/HelmChart/Public/kubernetes-agent/templates/daemonset.yaml
@@ -0,0 +1,56 @@
+{{- if .Values.logs.enabled }}
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: {{ include "kubernetes-agent.fullname" . }}-logs
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "kubernetes-agent.labels" . | nindent 4 }}
+    component: log-collector
+spec:
+  selector:
+    matchLabels:
+      {{- include "kubernetes-agent.selectorLabels" . | nindent 6 }}
+      component: log-collector
+  template:
+    metadata:
+      labels:
+        {{- include "kubernetes-agent.selectorLabels" . | nindent 8 }}
+        component: log-collector
+      annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/configmap-daemonset.yaml") . | sha256sum }}
+    spec:
+      serviceAccountName: {{ include "kubernetes-agent.serviceAccountName" . }}
+      containers:
+        - name: otel-collector
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          args:
+            - "--config=/etc/otel/otel-collector-config.yaml"
+          env:
+            - name: NODE_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+            - name: ONEUPTIME_API_KEY
+              valueFrom:
+                secretKeyRef:
+                  name: {{ include "kubernetes-agent.fullname" . }}
+                  key: api-key
+          resources:
+            {{- toYaml .Values.logs.resources | nindent 12 }}
+          volumeMounts:
+            - name: config
+              mountPath: /etc/otel
+              readOnly: true
+            - name: varlogpods
+              mountPath: /var/log/pods
+              readOnly: true
+      volumes:
+        - name: config
+          configMap:
+            name: {{ include "kubernetes-agent.fullname" . }}-daemonset
+        - name: varlogpods
+          hostPath:
+            path: /var/log/pods
+{{- end }}
--- a/HelmChart/Public/kubernetes-agent/templates/deployment.yaml
+++ b/HelmChart/Public/kubernetes-agent/templates/deployment.yaml
@@ -0,0 +1,67 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "kubernetes-agent.fullname" . }}
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "kubernetes-agent.labels" . | nindent 4 }}
+    component: metrics-collector
+spec:
+  replicas: {{ .Values.deployment.replicas }}
+  selector:
+    matchLabels:
+      {{- include "kubernetes-agent.selectorLabels" . | nindent 6 }}
+      component: metrics-collector
+  template:
+    metadata:
+      labels:
+        {{- include "kubernetes-agent.selectorLabels" . | nindent 8 }}
+        component: metrics-collector
+      annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/configmap-deployment.yaml") . | sha256sum }}
+    spec:
+      serviceAccountName: {{ include "kubernetes-agent.serviceAccountName" . }}
+      containers:
+        - name: otel-collector
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          args:
+            - "--config=/etc/otel/otel-collector-config.yaml"
+          env:
+            - name: NODE_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+            - name: CLUSTER_NAME
+              value: {{ .Values.clusterName | quote }}
+            - name: ONEUPTIME_API_KEY
+              valueFrom:
+                secretKeyRef:
+                  name: {{ include "kubernetes-agent.fullname" . }}
+                  key: api-key
+          ports:
+            - name: health
+              containerPort: 13133
+              protocol: TCP
+          livenessProbe:
+            httpGet:
+              path: /
+              port: health
+            initialDelaySeconds: 15
+            periodSeconds: 10
+          readinessProbe:
+            httpGet:
+              path: /
+              port: health
+            initialDelaySeconds: 5
+            periodSeconds: 10
+          resources:
+            {{- toYaml .Values.deployment.resources | nindent 12 }}
+          volumeMounts:
+            - name: config
+              mountPath: /etc/otel
+              readOnly: true
+      volumes:
+        - name: config
+          configMap:
+            name: {{ include "kubernetes-agent.fullname" . }}-deployment
--- a/HelmChart/Public/kubernetes-agent/templates/rbac.yaml
+++ b/HelmChart/Public/kubernetes-agent/templates/rbac.yaml
@@ -0,0 +1,88 @@
+{{- if .Values.serviceAccount.create }}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "kubernetes-agent.serviceAccountName" . }}
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "kubernetes-agent.labels" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+{{- end }}
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: {{ include "kubernetes-agent.fullname" . }}
+  labels:
+    {{- include "kubernetes-agent.labels" . | nindent 4 }}
+rules:
+  # For k8s_cluster receiver and k8sattributes processor
+  - apiGroups: [""]
+    resources:
+      - pods
+      - nodes
+      - nodes/proxy
+      - nodes/stats
+      - services
+      - endpoints
+      - namespaces
+      - events
+      - replicationcontrollers
+      - resourcequotas
+      - limitranges
+      - configmaps
+      - persistentvolumeclaims
+      - persistentvolumes
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["apps"]
+    resources:
+      - deployments
+      - replicasets
+      - statefulsets
+      - daemonsets
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["batch"]
+    resources:
+      - jobs
+      - cronjobs
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["autoscaling"]
+    resources:
+      - horizontalpodautoscalers
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["networking.k8s.io"]
+    resources:
+      - ingresses
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["extensions"]
+    resources:
+      - ingresses
+    verbs: ["get", "list", "watch"]
+  # For k8sobjects receiver to watch events
+  - apiGroups: ["events.k8s.io"]
+    resources:
+      - events
+    verbs: ["get", "list", "watch"]
+  # For kubeletstats receiver
+  - nonResourceURLs:
+      - /metrics
+      - /metrics/cadvisor
+    verbs: ["get"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: {{ include "kubernetes-agent.fullname" . }}
+  labels:
+    {{- include "kubernetes-agent.labels" . | nindent 4 }}
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: {{ include "kubernetes-agent.fullname" . }}
+subjects:
+  - kind: ServiceAccount
+    name: {{ include "kubernetes-agent.serviceAccountName" . }}
+    namespace: {{ .Release.Namespace }}
--- a/HelmChart/Public/kubernetes-agent/templates/secret.yaml
+++ b/HelmChart/Public/kubernetes-agent/templates/secret.yaml
@@ -0,0 +1,10 @@
+apiVersion: v1
+kind: Secret
+metadata:
+  name: {{ include "kubernetes-agent.fullname" . }}
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "kubernetes-agent.labels" . | nindent 4 }}
+type: Opaque
+data:
+  api-key: {{ .Values.oneuptime.apiKey | b64enc | quote }}
--- a/HelmChart/Public/kubernetes-agent/values.schema.json
+++ b/HelmChart/Public/kubernetes-agent/values.schema.json
@@ -0,0 +1,210 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "type": "object",
+  "required": ["oneuptime", "clusterName"],
+  "properties": {
+    "oneuptime": {
+      "type": "object",
+      "description": "OneUptime instance connection details",
+      "required": ["url", "apiKey"],
+      "properties": {
+        "url": {
+          "type": "string",
+          "description": "URL of your OneUptime instance (e.g., https://oneuptime.example.com)"
+        },
+        "apiKey": {
+          "type": "string",
+          "description": "Project API key from OneUptime (Settings > API Keys)"
+        }
+      },
+      "additionalProperties": false
+    },
+    "clusterName": {
+      "type": "string",
+      "description": "Unique name for this cluster (used as k8s.cluster.name attribute)"
+    },
+    "namespaceFilters": {
+      "type": "object",
+      "description": "Namespace filters to limit which namespaces are monitored",
+      "properties": {
+        "include": {
+          "type": "array",
+          "items": { "type": "string" },
+          "description": "If set, only these namespaces are monitored (empty = all namespaces)"
+        },
+        "exclude": {
+          "type": "array",
+          "items": { "type": "string" },
+          "description": "Namespaces to exclude from monitoring"
+        }
+      },
+      "additionalProperties": false
+    },
+    "image": {
+      "type": "object",
+      "description": "OTel Collector image configuration",
+      "properties": {
+        "repository": {
+          "type": "string"
+        },
+        "tag": {
+          "type": "string"
+        },
+        "pullPolicy": {
+          "type": "string",
+          "enum": ["Always", "IfNotPresent", "Never"]
+        }
+      },
+      "additionalProperties": false
+    },
+    "deployment": {
+      "type": "object",
+      "description": "Deployment (metrics + events collector) resource configuration",
+      "properties": {
+        "replicas": {
+          "type": "integer",
+          "minimum": 1
+        },
+        "resources": {
+          "type": "object",
+          "properties": {
+            "requests": {
+              "type": "object",
+              "properties": {
+                "cpu": { "type": "string" },
+                "memory": { "type": "string" }
+              },
+              "additionalProperties": false
+            },
+            "limits": {
+              "type": "object",
+              "properties": {
+                "cpu": { "type": "string" },
+                "memory": { "type": "string" }
+              },
+              "additionalProperties": false
+            }
+          },
+          "additionalProperties": false
+        }
+      },
+      "additionalProperties": false
+    },
+    "controlPlane": {
+      "type": "object",
+      "description": "Control plane monitoring configuration",
+      "properties": {
+        "enabled": {
+          "type": "boolean"
+        },
+        "etcd": {
+          "type": "object",
+          "properties": {
+            "endpoints": {
+              "type": "array",
+              "items": { "type": "string" }
+            },
+            "insecureSkipVerify": {
+              "type": "boolean"
+            }
+          },
+          "additionalProperties": false
+        },
+        "apiServer": {
+          "type": "object",
+          "properties": {
+            "endpoints": {
+              "type": "array",
+              "items": { "type": "string" }
+            },
+            "insecureSkipVerify": {
+              "type": "boolean"
+            }
+          },
+          "additionalProperties": false
+        },
+        "scheduler": {
+          "type": "object",
+          "properties": {
+            "endpoints": {
+              "type": "array",
+              "items": { "type": "string" }
+            },
+            "insecureSkipVerify": {
+              "type": "boolean"
+            }
+          },
+          "additionalProperties": false
+        },
+        "controllerManager": {
+          "type": "object",
+          "properties": {
+            "endpoints": {
+              "type": "array",
+              "items": { "type": "string" }
+            },
+            "insecureSkipVerify": {
+              "type": "boolean"
+            }
+          },
+          "additionalProperties": false
+        }
+      },
+      "additionalProperties": false
+    },
+    "logs": {
+      "type": "object",
+      "description": "Pod log collection via DaemonSet with filelog receiver",
+      "properties": {
+        "enabled": {
+          "type": "boolean"
+        },
+        "resources": {
+          "type": "object",
+          "properties": {
+            "requests": {
+              "type": "object",
+              "properties": {
+                "cpu": { "type": "string" },
+                "memory": { "type": "string" }
+              },
+              "additionalProperties": false
+            },
+            "limits": {
+              "type": "object",
+              "properties": {
+                "cpu": { "type": "string" },
+                "memory": { "type": "string" }
+              },
+              "additionalProperties": false
+            }
+          },
+          "additionalProperties": false
+        }
+      },
+      "additionalProperties": false
+    },
+    "collectionInterval": {
+      "type": "string",
+      "description": "Collection interval for metrics (e.g., 30s, 1m)"
+    },
+    "serviceAccount": {
+      "type": "object",
+      "description": "Service account configuration",
+      "properties": {
+        "create": {
+          "type": "boolean"
+        },
+        "name": {
+          "type": "string"
+        },
+        "annotations": {
+          "type": "object",
+          "additionalProperties": { "type": "string" }
+        }
+      },
+      "additionalProperties": false
+    }
+  },
+  "additionalProperties": false
+}
--- a/HelmChart/Public/kubernetes-agent/values.yaml
+++ b/HelmChart/Public/kubernetes-agent/values.yaml
@@ -0,0 +1,80 @@
+# OneUptime Kubernetes Agent Configuration
+
+# Required: Your OneUptime instance connection details
+oneuptime:
+  # URL of your OneUptime instance (e.g., https://oneuptime.example.com)
+  url: ""
+  # Project API key from OneUptime (Settings > API Keys)
+  apiKey: ""
+
+# Required: Unique name for this cluster (used as k8s.cluster.name attribute)
+clusterName: ""
+
+# Namespace filters — limit which namespaces are monitored
+namespaceFilters:
+  # If set, only these namespaces are monitored (empty = all namespaces)
+  include: []
+  # Namespaces to exclude from monitoring
+  exclude:
+    - kube-system
+
+# OTel Collector image configuration
+image:
+  repository: otel/opentelemetry-collector-contrib
+  tag: "0.96.0"
+  pullPolicy: IfNotPresent
+
+# Deployment (metrics + events collector) resource configuration
+deployment:
+  replicas: 1
+  resources:
+    requests:
+      cpu: 200m
+      memory: 512Mi
+    limits:
+      cpu: 1000m
+      memory: 2Gi
+
+# Control plane monitoring (etcd, API server, scheduler, controller manager)
+# Disabled by default — enable for self-managed clusters.
+# Managed K8s (EKS, GKE, AKS) typically don't expose control plane metrics.
+controlPlane:
+  enabled: false
+  etcd:
+    # Endpoints to scrape etcd metrics from
+    endpoints:
+      - https://localhost:2379/metrics
+    # TLS configuration for etcd
+    insecureSkipVerify: true
+  apiServer:
+    endpoints:
+      - https://localhost:6443/metrics
+    insecureSkipVerify: true
+  scheduler:
+    endpoints:
+      - https://localhost:10259/metrics
+    insecureSkipVerify: true
+  controllerManager:
+    endpoints:
+      - https://localhost:10257/metrics
+    insecureSkipVerify: true
+
+# Pod log collection via DaemonSet with filelog receiver
+logs:
+  enabled: true
+  resources:
+    requests:
+      cpu: 50m
+      memory: 128Mi
+    limits:
+      cpu: 200m
+      memory: 256Mi
+
+# Collection intervals
+collectionInterval: 30s
+
+# Service account configuration
+serviceAccount:
+  create: true
+  name: ""
+  annotations: {}
--- a/HelmChart/Public/oneuptime/templates/ai-agent.yaml
+++ b/HelmChart/Public/oneuptime/templates/ai-agent.yaml
@@ -1,4 +1,4 @@
-{{- if .Values.aiAgent.enabled }}
+{{- if and .Values.aiAgent.enabled (not .Values.deployment.disableDeployments) }}
 apiVersion: apps/v1
 kind: Deployment
 metadata:
--- a/HelmChart/Public/oneuptime/templates/app.yaml
+++ b/HelmChart/Public/oneuptime/templates/app.yaml
@@ -1,4 +1,4 @@
-{{- if $.Values.app.enabled }}
+{{- if and $.Values.app.enabled (not $.Values.deployment.disableDeployments) }}
 # OneUptime app Deployment
 apiVersion: apps/v1
 kind: Deployment
@@ -137,7 +137,7 @@ spec:
 ---
 {{- end }}

-{{- if $.Values.app.enabled }}
+{{- if and $.Values.app.enabled (not $.Values.deployment.disableDeployments) }}
 # OneUptime app Service
 {{- $appPorts := dict "port" $.Values.app.ports.http -}}
 {{- $appServiceArgs := dict "ServiceName" "app" "Ports" $appPorts "Release" $.Release "Values" $.Values -}}
--- a/HelmChart/Public/oneuptime/templates/cleanup-cron-job.yaml
+++ b/HelmChart/Public/oneuptime/templates/cleanup-cron-job.yaml
@@ -1,4 +1,4 @@
-{{- if $.Values.cronJobs.cleanup.enabled }}
+{{- if and $.Values.cronJobs.cleanup.enabled (not $.Values.deployment.disableDeployments) }}

 apiVersion: batch/v1
 kind: CronJob
--- a/HelmChart/Public/oneuptime/templates/home.yaml
+++ b/HelmChart/Public/oneuptime/templates/home.yaml
@@ -1,4 +1,4 @@
-{{- if $.Values.home.enabled }}
+{{- if and $.Values.home.enabled (not $.Values.deployment.disableDeployments) }}
 # OneUptime Home Deployment
 apiVersion: apps/v1
 kind: Deployment
@@ -126,7 +126,7 @@ spec:

 {{- end }}

-{{- if $.Values.home.enabled }}
+{{- if and $.Values.home.enabled (not $.Values.deployment.disableDeployments) }}
 # OneUptime home Service
 {{- $homePorts := $.Values.home.ports -}}
 {{- $homeServiceArgs := dict "ServiceName" "home" "Ports" $homePorts "Release" $.Release "Values" $.Values -}}
--- a/HelmChart/Public/oneuptime/templates/keda-scaledobjects.yaml
+++ b/HelmChart/Public/oneuptime/templates/keda-scaledobjects.yaml
@@ -3,7 +3,7 @@ KEDA ScaledObjects for various services
 */}}

 {{/* Telemetry KEDA ScaledObject */}}
-{{- if and .Values.keda.enabled .Values.telemetry.enabled .Values.telemetry.keda.enabled (not .Values.telemetry.disableAutoscaler) }}
+{{- if and .Values.keda.enabled .Values.telemetry.enabled .Values.telemetry.keda.enabled (not .Values.telemetry.disableAutoscaler) (not .Values.deployment.disableDeployments) }}
 {{- $metricsConfig := dict "enabled" .Values.telemetry.keda.enabled "minReplicas" .Values.telemetry.keda.minReplicas "maxReplicas" .Values.telemetry.keda.maxReplicas "pollingInterval" .Values.telemetry.keda.pollingInterval "cooldownPeriod" .Values.telemetry.keda.cooldownPeriod "triggers" (list (dict "query" "oneuptime_telemetry_queue_size" "threshold" .Values.telemetry.keda.queueSizeThreshold "port" .Values.telemetry.ports.http)) }}
 {{- $telemetryKedaArgs := dict "ServiceName" "telemetry" "Release" .Release "Values" .Values "MetricsConfig" $metricsConfig "DisableAutoscaler" .Values.telemetry.disableAutoscaler }}
 {{- include "oneuptime.kedaScaledObject" $telemetryKedaArgs }}
@@ -12,7 +12,7 @@ KEDA ScaledObjects for various services
 {{/* Probe KEDA ScaledObjects - one for each probe configuration */}}
 {{- range $key, $val := $.Values.probes }}
 {{- $probeEnabled := or (not (hasKey $val "enabled")) $val.enabled }}
-{{- if and $.Values.keda.enabled $probeEnabled (and $val.keda $val.keda.enabled) (not $val.disableAutoscaler) }}
+{{- if and $.Values.keda.enabled $probeEnabled (and $val.keda $val.keda.enabled) (not $val.disableAutoscaler) (not $.Values.deployment.disableDeployments) }}
 {{- $serviceName := printf "probe-%s" $key }}
 {{- $probePort := 3874 }}
 {{- if and $val.ports $val.ports.http }}
@@ -25,14 +25,14 @@ KEDA ScaledObjects for various services
 {{- end }}

 {{/* Worker KEDA ScaledObject */}}
-{{- if and .Values.keda.enabled .Values.worker.enabled .Values.worker.keda.enabled (not .Values.worker.disableAutoscaler) }}
+{{- if and .Values.keda.enabled .Values.worker.enabled .Values.worker.keda.enabled (not .Values.worker.disableAutoscaler) (not .Values.deployment.disableDeployments) }}
 {{- $metricsConfig := dict "enabled" .Values.worker.keda.enabled "minReplicas" .Values.worker.keda.minReplicas "maxReplicas" .Values.worker.keda.maxReplicas "pollingInterval" .Values.worker.keda.pollingInterval "cooldownPeriod" .Values.worker.keda.cooldownPeriod "triggers" (list (dict "query" "oneuptime_worker_queue_size" "threshold" .Values.worker.keda.queueSizeThreshold "port" .Values.worker.ports.http)) }}
 {{- $workerKedaArgs := dict "ServiceName" "worker" "Release" .Release "Values" .Values "MetricsConfig" $metricsConfig "DisableAutoscaler" .Values.worker.disableAutoscaler }}
 {{- include "oneuptime.kedaScaledObject" $workerKedaArgs }}
 {{- end }}

 {{/* AI Agent KEDA ScaledObject */}}
-{{- if and .Values.keda.enabled .Values.aiAgent.enabled .Values.aiAgent.keda.enabled (not .Values.aiAgent.disableAutoscaler) }}
+{{- if and .Values.keda.enabled .Values.aiAgent.enabled .Values.aiAgent.keda.enabled (not .Values.aiAgent.disableAutoscaler) (not .Values.deployment.disableDeployments) }}
 {{- $metricsConfig := dict "enabled" .Values.aiAgent.keda.enabled "minReplicas" .Values.aiAgent.keda.minReplicas "maxReplicas" .Values.aiAgent.keda.maxReplicas "pollingInterval" .Values.aiAgent.keda.pollingInterval "cooldownPeriod" .Values.aiAgent.keda.cooldownPeriod "triggers" (list (dict "query" "oneuptime_ai_agent_queue_size" "threshold" .Values.aiAgent.keda.queueSizeThreshold "port" .Values.aiAgent.ports.http)) }}
 {{- $aiAgentKedaArgs := dict "ServiceName" "ai-agent" "Release" .Release "Values" .Values "MetricsConfig" $metricsConfig "DisableAutoscaler" .Values.aiAgent.disableAutoscaler }}
 {{- include "oneuptime.kedaScaledObject" $aiAgentKedaArgs }}
--- a/HelmChart/Public/oneuptime/templates/nginx.yaml
+++ b/HelmChart/Public/oneuptime/templates/nginx.yaml
@@ -1,4 +1,4 @@
-{{- if $.Values.nginx.enabled }}
+{{- if and $.Values.nginx.enabled (not $.Values.deployment.disableDeployments) }}

 # OneUptime nginx Deployment
 apiVersion: apps/v1
--- a/HelmChart/Public/oneuptime/templates/probe.yaml
+++ b/HelmChart/Public/oneuptime/templates/probe.yaml
@@ -1,3 +1,4 @@
+{{- if not $.Values.deployment.disableDeployments }}
 {{- range $key, $val := $.Values.probes }}
 {{- if or (not (hasKey $val "enabled")) $val.enabled }}
 apiVersion: apps/v1
@@ -166,3 +167,4 @@ spec:
 ---

 {{- end }}
+{{- end }}
--- a/HelmChart/Public/oneuptime/templates/telemetry.yaml
+++ b/HelmChart/Public/oneuptime/templates/telemetry.yaml
@@ -1,4 +1,4 @@
-{{- if $.Values.telemetry.enabled }}
+{{- if and $.Values.telemetry.enabled (not $.Values.deployment.disableDeployments) }}
 # OneUptime telemetry Deployment

 apiVersion: apps/v1
@@ -137,7 +137,7 @@ spec:

 ---

-{{- if $.Values.telemetry.enabled }}
+{{- if and $.Values.telemetry.enabled (not $.Values.deployment.disableDeployments) }}
 # OneUptime telemetry Service
 {{- $telemetryPorts := dict "http" $.Values.telemetry.ports.http "grpc" $.Values.telemetry.ports.grpc -}}
 {{- $telemetryServiceArgs := dict "ServiceName" "telemetry" "Ports" $telemetryPorts "Release" $.Release "Values" $.Values -}}
--- a/HelmChart/Public/oneuptime/templates/test-server.yaml
+++ b/HelmChart/Public/oneuptime/templates/test-server.yaml
@@ -1,4 +1,4 @@
-{{- if $.Values.testServer.enabled }}
+{{- if and $.Values.testServer.enabled (not $.Values.deployment.disableDeployments) }}

 # OneUptime test-server Deployment
 {{- $testServerPorts := $.Values.testServer.ports -}}
--- a/HelmChart/Public/oneuptime/templates/worker.yaml
+++ b/HelmChart/Public/oneuptime/templates/worker.yaml
@@ -1,4 +1,4 @@
-{{- if $.Values.worker.enabled }}
+{{- if and $.Values.worker.enabled (not $.Values.deployment.disableDeployments) }}
 # OneUptime worker Deployment
 apiVersion: apps/v1
 kind: Deployment
@@ -128,7 +128,7 @@ spec:

 ---

-{{- if $.Values.worker.enabled }}
+{{- if and $.Values.worker.enabled (not $.Values.deployment.disableDeployments) }}
 # OneUptime worker Service
 {{- $workerPorts := $.Values.worker.ports -}}
 {{- $workerServiceArgs := dict "ServiceName" "worker" "Ports" $workerPorts "Release" $.Release "Values" $.Values -}}
--- a/HelmChart/Public/oneuptime/values.schema.json
+++ b/HelmChart/Public/oneuptime/values.schema.json
@@ -86,6 +86,11 @@
    "deployment": {
      "type": "object",
      "properties": {
+        "disableDeployments": {
+          "type": "boolean",
+          "description": "When set to true, no OneUptime deployments are provisioned. Only databases (Redis, ClickHouse, Postgres) will be running.",
+          "default": false
+        },
        "includeTimestampLabel": {
          "type": "boolean"
        },
--- a/HelmChart/Public/oneuptime/values.yaml
+++ b/HelmChart/Public/oneuptime/values.yaml
@@ -48,6 +48,8 @@ externalSecrets:
      passwordKey:

 deployment:
+  # When set to true, no OneUptime deployments are provisioned. Only databases (Redis, ClickHouse, Postgres) will be running.
+  disableDeployments: false
  # Default replica count for all deployments
  replicaCount: 1
  # Update strategy type for all deployments