Documentation
kagent#
A Helm chart for kagent, built with Google ADK
Requirements#
| Repository | Name | Version |
|---|---|---|
| file://../agents/argo-rollouts | argo-rollouts-agent | |
| file://../agents/cilium-debug | cilium-debug-agent | |
| file://../agents/cilium-manager | cilium-manager-agent | |
| file://../agents/cilium-policy | cilium-policy-agent | |
| file://../agents/helm | helm-agent | |
| file://../agents/istio | istio-agent | |
| file://../agents/k8s | k8s-agent | |
| file://../agents/kgateway | kgateway-agent | |
| file://../agents/observability | observability-agent | |
| file://../agents/promql | promql-agent | |
| file://../tools/grafana-mcp | grafana-mcp | |
| file://../tools/querydoc | querydoc | |
| oci://ghcr.io/kagent-dev/kmcp/helm | kmcp | ${KMCP_VERSION} |
| oci://ghcr.io/kagent-dev/tools/helm | kagent-tools | 0.1.1 |
Values#
| Key | Type | Default | Description |
|---|---|---|---|
| agents.argo-rollouts-agent.enabled | bool | true | |
| agents.argo-rollouts-agent.resources.limits.cpu | string | "1000m" | |
| agents.argo-rollouts-agent.resources.limits.memory | string | "1Gi" | |
| agents.argo-rollouts-agent.resources.requests.cpu | string | "100m" | |
| agents.argo-rollouts-agent.resources.requests.memory | string | "256Mi" | |
| agents.cilium-debug-agent.enabled | bool | true | |
| agents.cilium-debug-agent.resources.limits.cpu | string | "1000m" | |
| agents.cilium-debug-agent.resources.limits.memory | string | "1Gi" | |
| agents.cilium-debug-agent.resources.requests.cpu | string | "100m" | |
| agents.cilium-debug-agent.resources.requests.memory | string | "256Mi" | |
| agents.cilium-manager-agent.enabled | bool | true | |
| agents.cilium-manager-agent.resources.limits.cpu | string | "1000m" | |
| agents.cilium-manager-agent.resources.limits.memory | string | "1Gi" | |
| agents.cilium-manager-agent.resources.requests.cpu | string | "100m" | |
| agents.cilium-manager-agent.resources.requests.memory | string | "256Mi" | |
| agents.cilium-policy-agent.enabled | bool | true | |
| agents.cilium-policy-agent.resources.limits.cpu | string | "1000m" | |
| agents.cilium-policy-agent.resources.limits.memory | string | "1Gi" | |
| agents.cilium-policy-agent.resources.requests.cpu | string | "100m" | |
| agents.cilium-policy-agent.resources.requests.memory | string | "256Mi" | |
| agents.helm-agent.enabled | bool | true | |
| agents.helm-agent.resources.limits.cpu | string | "1000m" | |
| agents.helm-agent.resources.limits.memory | string | "1Gi" | |
| agents.helm-agent.resources.requests.cpu | string | "100m" | |
| agents.helm-agent.resources.requests.memory | string | "256Mi" | |
| agents.istio-agent.enabled | bool | true | |
| agents.istio-agent.resources.limits.cpu | string | "1000m" | |
| agents.istio-agent.resources.limits.memory | string | "1Gi" | |
| agents.istio-agent.resources.requests.cpu | string | "100m" | |
| agents.istio-agent.resources.requests.memory | string | "256Mi" | |
| agents.k8s-agent.enabled | bool | true | |
| agents.k8s-agent.resources.limits.cpu | string | "1000m" | |
| agents.k8s-agent.resources.limits.memory | string | "1Gi" | |
| agents.k8s-agent.resources.requests.cpu | string | "100m" | |
| agents.k8s-agent.resources.requests.memory | string | "256Mi" | |
| agents.kgateway-agent.enabled | bool | true | |
| agents.kgateway-agent.resources.limits.cpu | string | "1000m" | |
| agents.kgateway-agent.resources.limits.memory | string | "1Gi" | |
| agents.kgateway-agent.resources.requests.cpu | string | "100m" | |
| agents.kgateway-agent.resources.requests.memory | string | "256Mi" | |
| agents.observability-agent.enabled | bool | true | |
| agents.observability-agent.resources.limits.cpu | string | "1000m" | |
| agents.observability-agent.resources.limits.memory | string | "1Gi" | |
| agents.observability-agent.resources.requests.cpu | string | "100m" | |
| agents.observability-agent.resources.requests.memory | string | "256Mi" | |
| agents.promql-agent.enabled | bool | true | |
| agents.promql-agent.resources.limits.cpu | string | "1000m" | |
| agents.promql-agent.resources.limits.memory | string | "1Gi" | |
| agents.promql-agent.resources.requests.cpu | string | "100m" | |
| agents.promql-agent.resources.requests.memory | string | "256Mi" | |
| controller.a2aBaseUrl | string | http://<fullname>-controller.<namespace>.svc.cluster.local:<port> | The base URL of the A2A Server endpoint, as advertised to clients. |
| controller.agentDeployment | object | {"serviceAccountName":""} | Global deployment defaults applied to all agent pods. Per-agent settings in the Agent CRD take precedence over these defaults. |
| controller.agentDeployment.serviceAccountName | string | "" (auto-create per-agent ServiceAccount) | Default ServiceAccount name for agent pods. When set, agent pods that don't specify an explicit serviceAccountName will use this ServiceAccount instead of creating a per-agent one. Useful for Workload Identity (GCP, AWS IRSA, Azure Workload Identity). Precedence: agent-level serviceAccountName > this default > auto-created SA. |
| controller.agentImage.pullPolicy | string | "" | |
| controller.agentImage.registry | string | "" | |
| controller.agentImage.repository | string | "kagent-dev/kagent/app" | |
| controller.agentImage.tag | string | "" | |
| controller.env | list | [] | |
| controller.envFrom | list | [] | |
| controller.image.pullPolicy | string | "" | |
| controller.image.registry | string | "" | |
| controller.image.repository | string | "kagent-dev/kagent/controller" | |
| controller.image.tag | string | "" | |
| controller.loglevel | string | "info" | |
| controller.nodeSelector | object | {} | Node labels to match for Pod scheduling. |
| controller.replicas | int | 1 | |
| controller.resources.limits.cpu | int | 2 | |
| controller.resources.limits.memory | string | "512Mi" | |
| controller.resources.requests.cpu | string | "100m" | |
| controller.resources.requests.memory | string | "128Mi" | |
| controller.service.ports.port | int | 8083 | |
| controller.service.ports.targetPort | int | 8083 | |
| controller.service.type | string | "ClusterIP" | |
| controller.skillsInitImage | object | {"pullPolicy":"","registry":"","repository":"kagent-dev/kagent/skills-init","tag":""} | The image used by the skills-init container to clone skills from Git and pull OCI skill images. |
| controller.streaming.initialBufSize | string | "4Ki" | |
| controller.streaming.maxBufSize | string | "1Mi" | |
| controller.streaming.timeout | string | "600s" | |
| controller.tolerations | list | [] | Node taints which will be tolerated for Pod scheduling. |
| controller.volumeMounts | list | [] | |
| controller.volumes | list | [] | |
| controller.watchNamespaces | list | [] (watches all available namespaces) | Namespaces the controller should watch. If empty, the controller will watch ALL available namespaces. |
| database.postgres.bundled.enabled | bool | true | Deploy the bundled PostgreSQL pod and PVC. Set to false to disable the bundled instance and provide your own via url or urlFile. |
| database.postgres.bundled.image.registry | string | "docker.io" | Bundled PostgreSQL image registry. |
| database.postgres.bundled.image.repository | string | "library" | Bundled PostgreSQL image repository (org/namespace). |
| database.postgres.bundled.image.name | string | "postgres" | Bundled PostgreSQL image name. |
| database.postgres.bundled.image.tag | string | "18" | Bundled PostgreSQL image tag. |
| database.postgres.bundled.image.pullPolicy | string | "IfNotPresent" | Bundled PostgreSQL image pull policy. |
| database.postgres.bundled.storage | string | "500Mi" | PersistentVolumeClaim size for the bundled PostgreSQL instance. |
| database.postgres.bundled.resources.requests.cpu | string | "250m" | CPU request for the bundled PostgreSQL container. |
| database.postgres.bundled.resources.requests.memory | string | "256Mi" | Memory request for the bundled PostgreSQL container. |
| database.postgres.bundled.resources.limits.cpu | string | "500m" | CPU limit for the bundled PostgreSQL container. |
| database.postgres.bundled.resources.limits.memory | string | "512Mi" | Memory limit for the bundled PostgreSQL container. |
| database.postgres.url | string | "" | External PostgreSQL connection string. Always used if set, regardless of bundled.enabled. |
| database.postgres.urlFile | string | "" | Path to a file containing the database URL. Takes precedence over url when set. Always used if set, regardless of bundled.enabled. |
| database.postgres.vectorEnabled | bool | false | Enable pgvector extension and memory table migration. Set to true when using a PostgreSQL server that has pgvector installed. Required for vector-based memory features. |
| fullnameOverride | string | "" | |
| grafana-mcp.grafana.serviceAccountToken | string | "" | |
| grafana-mcp.grafana.url | string | "grafana.kagent:3000/api" | |
| grafana-mcp.resources.limits.cpu | string | "500m" | |
| grafana-mcp.resources.limits.memory | string | "512Mi" | |
| grafana-mcp.resources.requests.cpu | string | "100m" | |
| grafana-mcp.resources.requests.memory | string | "128Mi" | |
| imagePullPolicy | string | "IfNotPresent" | |
| imagePullSecrets | list | [] | |
| kagent-tools.enabled | bool | true | |
| kagent-tools.nameOverride | string | "tools" | |
| kagent-tools.replicaCount | int | 1 | |
| kagent-tools.resources.limits.cpu | string | "1000m" | |
| kagent-tools.resources.limits.memory | string | "1Gi" | |
| kagent-tools.resources.requests.cpu | string | "100m" | |
| kagent-tools.resources.requests.memory | string | "256Mi" | |
| kagent-tools.tools.loglevel | string | "debug" | |
| kagent-tools.tools.metrics.port | int | 8085 | |
| kmcp.enabled | bool | true | |
| kmcp.fullnameOverride | string | "" | |
| kmcp.nameOverride | string | "kmcp" | |
| kmcp.namespaceOverride | string | "" | |
| labels | object | {} | Additional labels to add to all Kubernetes resources |
| nameOverride | string | "" | |
| namespaceOverride | string | .Release.Namespace | Override the namespace |
| nodeSelector | object | {} | Node labels to match for Pod scheduling. |
| otel.logging.enabled | bool | false | |
| otel.logging.exporter.otlp.endpoint | string | "" | |
| otel.logging.exporter.otlp.insecure | bool | true | |
| otel.logging.exporter.otlp.timeout | int | 15 | |
| otel.tracing.enabled | bool | false | |
| otel.tracing.exporter.otlp.endpoint | string | "" | |
| otel.tracing.exporter.otlp.insecure | bool | true | |
| otel.tracing.exporter.otlp.protocol | string | "grpc" | |
| otel.tracing.exporter.otlp.timeout | int | 15 | |
| podAnnotations | object | {} | |
| podSecurityContext | object | {} | |
| providers.anthropic.apiKeySecretKey | string | "ANTHROPIC_API_KEY" | |
| providers.anthropic.apiKeySecretRef | string | "kagent-anthropic" | |
| providers.anthropic.model | string | "claude-3-5-haiku-20241022" | |
| providers.anthropic.provider | string | "Anthropic" | |
| providers.azureOpenAI.apiKeySecretKey | string | "AZUREOPENAI_API_KEY" | |
| providers.azureOpenAI.apiKeySecretRef | string | "kagent-azure-openai" | |
| providers.azureOpenAI.config.apiVersion | string | "2023-05-15" | |
| providers.azureOpenAI.config.azureAdToken | string | "" | |
| providers.azureOpenAI.config.azureDeployment | string | "" | |
| providers.azureOpenAI.config.azureEndpoint | string | "" | |
| providers.azureOpenAI.model | string | "gpt-4.1-mini" | |
| providers.azureOpenAI.provider | string | "AzureOpenAI" | |
| providers.default | string | "openAI" | |
| providers.gemini.apiKeySecretKey | string | "GOOGLE_API_KEY" | |
| providers.gemini.apiKeySecretRef | string | "kagent-gemini" | |
| providers.gemini.model | string | "gemini-2.0-flash-lite" | |
| providers.gemini.provider | string | "Gemini" | |
| providers.ollama.config.host | string | "host.docker.internal:11434" | |
| providers.ollama.config.options.num_ctx | string | "64000" | |
| providers.ollama.model | string | "llama3.2" | |
| providers.ollama.provider | string | "Ollama" | |
| providers.openAI.apiKeySecretKey | string | "OPENAI_API_KEY" | |
| providers.openAI.apiKeySecretRef | string | "kagent-openai" | |
| providers.openAI.model | string | "gpt-4.1-mini" | |
| providers.openAI.provider | string | "OpenAI" | |
| proxy.url | string | "" | |
| querydoc.image.pullPolicy | string | "IfNotPresent" | |
| querydoc.image.registry | string | "ghcr.io" | |
| querydoc.image.repository | string | "kagent-dev/doc2vec/mcp" | |
| querydoc.image.tag | string | "1.1.14" | |
| querydoc.openai.apiKey | string | "" | |
| querydoc.replicas | int | 1 | |
| querydoc.resources.limits.cpu | string | "500m" | |
| querydoc.resources.limits.memory | string | "512Mi" | |
| querydoc.resources.requests.cpu | string | "100m" | |
| querydoc.resources.requests.memory | string | "128Mi" | |
| registry | string | "cr.kagent.dev" | |
| securityContext | object | {} | |
| tag | string | "" | |
| tolerations | list | [] | Node taints which will be tolerated for Pod scheduling. |
| tools.grafana-mcp.enabled | bool | true | |
| tools.querydoc.enabled | bool | true | |
| ui.env | object | {} | |
| ui.image.pullPolicy | string | "" | |
| ui.image.registry | string | "" | |
| ui.image.repository | string | "kagent-dev/kagent/ui" | |
| ui.image.tag | string | "" | |
| ui.nodeSelector | object | {} | Node labels to match for Pod scheduling. |
| ui.replicas | int | 1 | |
| ui.resources.limits.cpu | string | "1000m" | |
| ui.resources.limits.memory | string | "1Gi" | |
| ui.resources.requests.cpu | string | "100m" | |
| ui.resources.requests.memory | string | "256Mi" | |
| ui.service.ports.port | int | 8080 | |
| ui.service.ports.targetPort | int | 8080 | |
| ui.service.type | string | "ClusterIP" | |
| ui.tolerations | list | [] | Node taints which will be tolerated for Pod scheduling. |
Kagent Lab: Discover kagent and kmcp
Free, on‑demand lab: build custom AI agents with kagent and integrate tools via kmcp on Kubernetes.