NightMend
A self-hosted, open-source monitoring platform that uses an LLM to analyze alerts, pick a runbook, and execute automated remediation, in addition to standard metrics and PromQL dashboards.
NightMend is an open-source monitoring platform that adds AI-driven root-cause analysis and automated remediation on top of conventional metrics collection. It uses DeepSeek to read logs, metrics, and topology to find the likely cause of an alert, selects a matching runbook from a set of built-in auto-remediation scripts covering actions such as disk cleanup, service restarts, memory-pressure handling, log rotation, and Docker cleanup, then executes the fix with safety checks and an approval workflow.
It supports PromQL queries and includes Model Context Protocol integration so a connected AI coding assistant can query live production data directly. Deployment is Docker-based and self-hosted; on first startup the backend creates its database tables, alert rules, and dashboard components automatically, and the first registered account becomes the administrator.
The project describes itself as early-stage and recommends established tools for mission-critical systems at scale.