Docs
Documentation
Agentgateway
Setup

Setup

Set up an agentgateway proxy.

Before you begin

  1. Install kgateway and enable the agentgateway integration.

  2. Verify that the agentgateway and AI extensions are enabled.

    helm get values kgateway -n kgateway-system -o yaml

    Example output:

    
agentGateway:
  enabled: true

Set up an agentgateway proxy

  1. Create a Gateway that uses the agentgateway GatewayClass.

    kubectl apply -f- <<EOF
kind: Gateway
apiVersion: gateway.networking.k8s.io/v1
metadata:
  name: agentgateway
  namespace: kgateway-system
  labels:
    app: agentgateway
spec:
  gatewayClassName: agentgateway
  listeners:
  - protocol: HTTP
    port: 8080
    name: http
    allowedRoutes:
      namespaces:
        from: All
EOF

  2. Verify that the agentgateway proxy is created.

    • Gateway: Note that it might take a few minutes for an address to be assigned.
    • Pod for agentgateway proxy: The pod has one container: agent-gateway.
    kubectl get gateway agentgateway -n kgateway-system
kubectl get deployment agentgateway -n kgateway-system

    Example output:

    NAME           CLASS          ADDRESS                                                                  PROGRAMMED   AGE
agentgateway   agentgateway   a1cff4bd974a34d8b882b2fa01d357f0-119963959.us-east-2.elb.amazonaws.com   True         6m9s
NAME           READY   UP-TO-DATE   AVAILABLE   AGE
agentgateway   1/1     1            1           6m11s

  3. Get the external address of the gateway and save it in an environment variable. 

    export INGRESS_GW_ADDRESS=$(kubectl get svc -n kgateway-system agentgateway -o jsonpath="{.status.loadBalancer.ingress[0]['hostname','ip']}")
echo $INGRESS_GW_ADDRESS  
    kubectl port-forward deployment/agentgateway -n kgateway-system 8080:8080

Next

Explore how you can use your agentgateway by checking out guides for the most common use cases:

AboutInference routing