Prometheus
Time-series database and monitoring server that scrapes metrics endpoints on a schedule, stores samples locally, and evaluates PromQL queries, recording rules and alert conditions against them.
Essential monitoring infrastructure that provides insight into your AI stack's performance and health. Prometheus collects detailed metrics from all your services, Grafana transforms that data into beautiful, actionable dashboards, and cAdvisor specifically monitors Docker container resource usage. This combination solves the critical problem of understanding what's happening inside your AI systems - which services are consuming resources, how fast your models are responding, and whether everything is running smoothly. The setup provides the foundation for identifying bottlenecks, planning capacity, and troubleshooting issues before they become problems.
Time-series database and monitoring server that scrapes metrics endpoints on a schedule, stores samples locally, and evaluates PromQL queries, recording rules and alert conditions against them.
Dashboard and visualisation server that queries time-series, log and SQL data sources directly and renders panels, with alert rules, notification routing and dashboards defined as JSON.
Container resource monitor that discovers running containers automatically and exports per-container CPU, memory, filesystem and network statistics in Prometheus format and a built-in live view.