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

Visualize standalone agentgateway metrics in Grafana with the pre-built dashboard for binary, Docker, and Helm deployments.

Grafana is an open-source visualization platform that turns time-series data into dashboards, graphs, and alerts. It is the standard way to visualize agentgateway metrics that are collected by Prometheus, and supports correlating metrics with traces by adding Jaeger as a second data source in the same Grafana instance.

Agentgateway ships a pre-built standalone dashboard for binary, Docker, and standalone Helm deployments. It covers requests, latency, LLM traffic, MCP traffic, and runtime statistics without requiring Kubernetes namespace, gateway, or pod labels.

Use the PromQL queries to add custom panels or alerts.

Before you begin

Set up a Prometheus instance so that you can start collecting metrics and feeding them into Grafana. Do not run that guide’s cleanup step until you finish this one, if you use the Kubernetes installation steps, because both guides use the monitoring namespace.

Use Grafana in Kubernetes

The standalone dashboard includes request rates by status, route, and reason; request latency; LLM token usage, time to first token, and inter-chunk latency; MCP calls; and runtime statistics. The Kubernetes control-plane dashboard is a separate dashboard that requires Kubernetes labels.

1. Add the Grafana Helm repository and install Grafana.

   helm repo add grafana https://grafana.github.io/helm-charts
   helm install grafana grafana/grafana -n monitoring --create-namespace

2. Verify that the Grafana pod is running.

   kubectl get pods -n monitoring

3. Get the Grafana admin password.

   kubectl get secret -n monitoring grafana -o jsonpath="{.data.admin-password}" | base64 --decode

4. Forward the Grafana port to access the UI.

   kubectl port-forward -n monitoring svc/grafana 3001:80

5. Access Grafana at http://localhost:3001. Log in with the admin username and the password that you created in the previous step.

6. Add a Prometheus data source.

   1. Go to Connections → Add new connection.
   2. Search for and select the Prometheus plugin, then click Add new data source.
   3. Set the URL to your in-cluster Prometheus service, such as http://kube-prometheus-stack-prometheus.monitoring.svc.cluster.local:9090.
   4. Click Save & Test.

7. Download the agentgateway dashboard JSON.

   curl -L "https://raw.githubusercontent.com/agentgateway/agentgateway/main/controller/install/helm/agentgateway-standalone/files/agentgateway-dashboard.json" \
     -o agentgateway-dashboard.json

8. In Grafana, go to Dashboards → New → Import.

9. Click Upload dashboard JSON file and select the agentgateway-dashboard.json file.

10. Select your Prometheus data source and click Import.

11. When you are done, remove Grafana and the monitoring namespace.

    helm uninstall grafana -n monitoring
    kubectl delete namespace monitoring

Use Grafana with binary or Docker

1. Run Grafana with Docker.

   docker run -d --name grafana \
     -p 3001:3000 \
     grafana/grafana:latest

2. Access the Grafana UI at http://localhost:3001. Use the admin username and admin password to log into Grafana.

3. Add a Prometheus data source.

   1. Go to Connections → Add new connection.
   2. Search for and select the Prometheus plugin, then click Add new data source.
   3. Set the Prometheus server URL to http://host.docker.internal:9090.
   4. Click Save & Test.

4. Download and import the standalone dashboard.

   curl -L "https://raw.githubusercontent.com/agentgateway/agentgateway/main/controller/install/helm/agentgateway-standalone/files/agentgateway-dashboard.json" \
     -o agentgateway-dashboard.json

   In Grafana, go to Dashboards → New → Import, upload the JSON file, select your Prometheus data source, and click Import. The dashboard does not require Kubernetes labels on your metrics.

   To add your own panels, select New dashboard, add a visualization, and enter one of the Common PromQL queries in the query editor’s Code view.

5. When you are done, remove the Grafana container.

   docker rm -f grafana

Common PromQL queries

Use these queries to build custom panels or alerts. To enter a raw PromQL query in Grafana, switch the query editor from Builder to Code mode by using the toggle in the query section.

Add a Jaeger data source for traces

To correlate metrics with traces in the same Grafana instance:

1. Go to Connections → Add new connection.
2. Search for and select the Jaeger plugin, then click Add new data source.
3. Set the URL to your Jaeger instance, such as http://jaeger:16686.
4. Click Save & Test.