HolmesGPT SRE Agent in CNCF Sandbox Ships Skills System and VictoriaLogs Toolset — Agentic Troubleshooting for Kubernetes at 2,356 Stars

GitHub·medium signal

HolmesGPT is an AI agent for investigating production incidents that actively decides what data to fetch, runs targeted queries, and iteratively refines hypotheses. Accepted into CNCF Sandbox October 2025. Recent updates introduce Skills functionality for custom tool integrations via configuration and VictoriaLogs toolset for log search/analysis. Can run 24/7 in background, spots problems before customers notice, and messages fixes to Slack.