Ongrid
Ongrid is a self-hosted operations AI agent that understands an organization's infrastructure, correlates metrics, logs and traces to find a root cause, and can act on it from Slack, Telegram, Lark or DingTalk, with no inbound ports required on the monitored hosts.
Ongrid is an operations AI agent that investigates infrastructure problems and can fix them from a chat channel such as Slack or Telegram. A coordinator agent dispatches work to specialist SRE, network and database subagents, and an alert can trigger an investigator agent that walks the system topology, correlates metrics, logs and traces, and pins a probable cause to a source-code line.
It self-hosts with a single install command that brings up a full observability stack, including Prometheus, Loki, Tempo and Grafana, and reaches monitored hosts through an outbound-only edge connection so no inbound ports are opened. It also includes Kubernetes lifecycle management, browser-based SSH into any enrolled host, and support for bringing your own model from several providers.