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

Grafana

Visualize agentgateway metrics and traces with Grafana

Use Grafana to create dashboards for agentgateway metrics and visualize distributed traces.

Quick start

Run Grafana with Docker:

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

Access Grafana at http://localhost:3001 (default credentials: admin/admin).

Add Prometheus data source

1. Go to Configuration → Data Sources
2. Click Add data source
3. Select Prometheus
4. Set URL to http://prometheus:9090 (or your Prometheus URL)
5. Click Save & Test

Add Jaeger data source

For distributed tracing:

1. Go to Configuration → Data Sources
2. Click Add data source
3. Select Jaeger
4. Set URL to http://jaeger:16686 (or your Jaeger URL)
5. Click Save & Test

Import the agentgateway dashboard

Instead of building panels by hand, import the pre-built agentgateway dashboard. This dashboard is maintained in the agentgateway repository and visualizes both the control and data plane metrics that agentgateway exposes.

1. Download the agentgateway Grafana dashboard.

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

2. In Grafana, go to Dashboards > New > Import.

3. Click Upload dashboard JSON file and select the agentgateway-dashboard.json file that you downloaded.

4. Select your Prometheus data source, then click Import.

5. Verify that you see metrics, such as the request rate by gateway, LLM token consumption, or MCP tool calls. The dashboard includes the following sections.

   Section	Metric	Description
   Overview	Memory	The working set memory that each agentgateway proxy pod consumes.
   Overview	CPU	The CPU usage rate for each agentgateway proxy pod.
   Requests	Requests (by Pod)	The request rate that each agentgateway proxy pod handles.
   Requests	Requests (by Gateway)	The request rate for each gateway.
   Requests	Requests (by Status)	The request rate grouped by HTTP response status.
   Requests	Requests (by Reason)	The request rate grouped by the response reason.
   LLM	Token Consumption	The rate of tokens that LLM requests consume, grouped by token type, model, and gateway.
   LLM	Time To First Token	The time that it takes the LLM provider to return the first token of a response.
   LLM	Request Time	The total duration of LLM requests.
   LLM	Tokens Per Second	The rate at which the LLM provider returns output tokens.
   MCP	MCP Calls (by method)	The rate of MCP requests grouped by JSON-RPC method.
   MCP	Tool Calls (by tool)	The rate of MCP tool calls grouped by server, resource, and tool.
   Latency	Latency by Route	The 50th, 95th, and 99th percentile request latency for each gateway and route.
   XDS	XDS Messages by Type	The rate of xDS configuration messages that the control plane sends, grouped by resource type.
   XDS	XDS Average Message Size	The average size of xDS messages, grouped by resource type.
   Runtime	Cgroup Memory	The cgroup memory usage for each agentgateway proxy pod, such as working set, anonymous, file, and kernel memory.
   Runtime	Process Memory	The process-level memory for each agentgateway proxy pod, such as RSS, PSS, private, shared, and swap memory.
   Runtime	Tokio Runtime	The async runtime statistics for each agentgateway proxy pod, such as the worker count, number of alive tasks, and global queue depth.
   Runtime	Build Versions	The agentgateway build versions that are running, grouped by tag.

Build custom panels

If you prefer to build your own dashboard, you can create panels from the metrics that agentgateway exposes. The following examples show common queries.

Request rate

rate(agentgateway_requests_total[5m])

Request duration (p99)

histogram_quantile(0.99, rate(agentgateway_request_duration_seconds_bucket[5m]))

Error rate

rate(agentgateway_requests_total{status=~"5.."}[5m]) / rate(agentgateway_requests_total[5m])

LLM token usage

rate(agentgateway_llm_tokens_total[5m])

Docker Compose example

version: '3'
services:
  agentgateway:
    image: ghcr.io/agentgateway/agentgateway:latest
    ports:
      - "3000:3000"
      - "15020:15020"

  prometheus:
    image: prom/prometheus:latest
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml

  grafana:
    image: grafana/grafana:latest
    ports:
      - "3001:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin
    volumes:
      - grafana-storage:/var/lib/grafana

volumes:
  grafana-storage:

Learn more