HolmesGPT

HolmesGPT is an open-source AI agent that investigates production incidents and finds root causes. Robusta.Dev created it, and CNCF accepted it as a Sandbox project on October 8, 2025. It runs an agentic loop over live observability data through built-in toolsets for Prometheus, Grafana, Datadog, Kubernetes and others, plus custom REST API toolsets, with server-side filtering and per-tool memory limits to keep large payloads out of context. An operator mode runs scheduled health checks in the background, and it can pull alerts from AlertManager, PagerDuty or Jira and write findings back.