For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.

Devin Desktop

Configure Devin Desktop AI code editor to use agentgateway running in Kubernetes

Configure Devin Desktop, the AI-powered code editor from Cognition (formerly Windsurf), to route requests to your LLM through your agentgateway proxy.

Before you begin

1. Set up an agentgateway proxy.
2. Set up access to the OpenAI LLM provider.

Get the gateway URL

export INGRESS_GW_ADDRESS=$(kubectl get svc -n agentgateway-system agentgateway-proxy \
  -o jsonpath='{.status.loadBalancer.ingress[0].ip}')

echo "Gateway address: $INGRESS_GW_ADDRESS"

export INGRESS_GW_ADDRESS=$(kubectl get svc -n agentgateway-system agentgateway-proxy \
  -o jsonpath='{.status.loadBalancer.ingress[0].hostname}')

echo "Gateway address: $INGRESS_GW_ADDRESS"

kubectl port-forward -n agentgateway-system svc/agentgateway-proxy 8080:80

Configure Devin Desktop

Configure Devin Desktop to route LLM requests through agentgateway. For more information, review the Devin Desktop documentation.

1. Open Devin Desktop Settings.

   • macOS: Cmd + , or Devin Desktop > Settings
   • Windows/Linux: Ctrl + , or File > Preferences > Settings

2. Search for Http: Proxy.

3. Enter your agentgateway URL.

   http://<INGRESS_GW_ADDRESS>/<route-path>

   For example, if your HTTPRoute uses path /openai on your ai-example.com secured host, use https://ai-example.com/openai.

4. Save the settings.

Verify the connection

1. Open the Devin Desktop chat panel.
2. Send a message such as “test”.
3. Devin Desktop responds through your agentgateway backend.