Versus Incident is an AI SRE agent that learns normal behavior across logs, metrics, and traces, then detects and investigates unusual changes. It proposes SLOs and routes relevant incidents to chat and on-call platforms, with a free MIT-licensed self-hosted core and hosted enterprise capabilities.
In the LLM eval & observability space, Versus Incident takes a focused approach. It focuses on reducing alert fatigue by detecting novel system behavior and investigating incidents before routing only meaningful issues to on-call teams. Versus Incident is a B2B product aimed at SRE and DevOps teams. Versus Incident is commercial open source (MIT). It ships for the web, and it can be self-hosted.
Behind Versus Incident is VersusControl, and it first shipped in 2025. The project is developed in the open on GitHub with 1.4k stars and 35 commits in the last 90 days. Among its 10 catalogued features are anomaly detection, read-only investigation, and runbook recall. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do