Skip to main content

Prometheus Metrics

Prometheus Metrics

Prometheus collects and stores time-series metrics for monitoring agents, services, and infrastructure.

Installation

# Docker
docker run -d -p 9090:9090 prom/prometheus

# Kubernetes
helm install prometheus prometheus-community/prometheus -n observability

Configuration

# prometheus.yml
global:
  scrape_interval: 15s
  evaluation_interval: 15s

scrape_configs:
  - job_name: 'agent-tracer'
    static_configs:
      - targets: ['localhost:3007']

  - job_name: 'agents'
    kubernetes_sd_configs:
      - role: pod
        namespaces:
          names: ['agents']

Metrics

Agent Metrics

# Task completion rate
rate(agent_tasks_completed_total[5m])

# Error rate
rate(agent_errors_total[5m])

# Task duration
histogram_quantile(0.95, agent_task_duration_seconds_bucket)

# LLM cost
sum(llm_cost_usd_total)

Related Pages