VersusControl/versus-incident

Versus Incident is the self-hosted AI SRE agent. It learns what your system normally look like and escalates only what is new or unexpected issues; routing to your chat channels and on-call platform.

What it solves

Versus Incident acts as an AI-powered Site Reliability Engineering (SRE) teammate that automates the detection and management of system incidents. It eliminates the need to manually maintain complex alert rules by automatically learning what "normal" system behavior looks like and alerting teams only when new or unexpected anomalies appear in logs.

How it works

Versus processes incidents through two primary channels:

  1. AI SRE Agent: This agent monitors log sources (via files or Elasticsearch). It operates in three modes: training (learning patterns without alerting), shadow (logging potential alerts for review), and detect (actively creating incidents). When in detect mode, the AI triages the issue to provide a summary, severity level, and suggested next steps.
  2. Webhook Alerts: It provides a REST API endpoint that accepts JSON payloads from existing monitoring tools like Prometheus Alertmanager, Grafana, Sentry, and CloudWatch SNS.

Once an incident is triggered, Versus templates the message and fans it out to multiple notification channels (Slack, Teams, Telegram, etc.) and can escalate to on-call providers like PagerDuty or AWS Incident Manager if not acknowledged in time.

Who it’s for

It is designed for DevOps and SRE teams who want to reduce alert fatigue by moving away from static rules and automating the initial triage of system errors.

Highlights

  • Automated Pattern Learning: Learns normal log patterns to detect brand-new errors without manual rule configuration.
  • Multi-channel Notifications: Supports Slack, Microsoft Teams, Telegram, Viber, Email, and Lark.
  • On-Call Integration: Integrates with PagerDuty, Opsgenie, incident.io, and ServiceNow for escalation.
  • Flexible Log Filtering: Uses regex pre-filters to ignore noise (like 200-OK responses) before the AI processes the data.
  • Custom Templating: Allows users to define alert messages using Go templates.

Related

  • Project
    Tracer-Cloud/opensre

    OpenSRE is an open‑source framework for AI‑driven Site Reliability Engineering agents. It connects to 60+ observability, cloud, and incident‑management tools, fetches relevant context, runs a tool‑calling reasoning loop, and returns evidence‑backed diagnoses or remediation actions. Users can interact via an interactive shell, a headless CLI, or a Python API, and deploy the system via a managed cloud gateway, self‑hosted container, or EC2 AMI. The project is in public‑alpha (v0.1) and licensed under Apache 2.0.

  • Project
    FunnyWolf/agentic-soc-platform

    An open-source security operations platform that uses Agentic AI to automate alert triage, investigation, and knowledge accumulation for security teams.

  • Project
    HolmesGPT/holmesgpt

    An open-source AI agent for SREs that automates production incident investigation and root cause analysis across any infrastructure stack.

  • Project
    CloudDetail/apo

    An intelligent observability platform that uses AI agents and a specialized data plane to automate root cause analysis and diagnostic workflows for system monitoring.

  • Project
    William-Lu-stack/Flawless

    An AI-native SRE control plane for Kubernetes that automates the incident lifecycle from diagnosis to verified recovery using a guarded agentic loop.