Self-hosted · Open-core · Read-only by design
Infrastructure alerts,
decoded.
Monitoring tools tell you what fired, but rarely enough to investigate. AlertINT is a self-hosted, open-core agent runtime that turns infrastructure alerts into incident context your AI agent reads directly over MCP.
{
"source": "alertmanager",
"runtime": "alertint",
"access": "mcp",
"telemetry": "prometheus:read_only",
"writes": false
}How it works
One local runtime, two paths.
AlertINT runs locally on your infra between your monitoring stack (Alertmanager, Prometheus et al), your telemetry, and your AI agent. See Docs for full info.
Runtime path
Alert Ingestion
Monitoring/observability tool sends alert to AlertINT.
Data Persistence / Correlation
AlertINT stores and groups the alerts.
AI Synthesis
AlertINT uses AI analysis to gather data about the potential incident.
Outbound Notification
Slack (or others) receive a notification with full context.
AlertINT
Operator path
Agent Entry
Use Claude Code, Cursor, Windsurf or another MCP client to connect.
Evidence Query
The agent utilizes AlertINT to get recent incidents and evidence, and enhance it with live data from your systems.
Decision Point
You decide the next check — with full context in hand.
Read-only
Observes and reports by default, never touches your infrastructure.
Self-hosted
Your alert data and incident context stay inside your infrastructure. We enjoy privacy as much as you do.
Open-core
The core runtime is open-core and always will be.
MCP-first
Your AI agent inspects real incident state and live data, not pasted text.
Get it
A single self-hosted binary.
Available on GitHub*. Run the server, point monitoring tools, connect MCP, and start preventing incidents.
*working on opening the GitHub repo as soon as it's ready for a public release.