alertint-agent

mcp
Security Audit
Fail
Health Warn
  • License — License: NOASSERTION
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Fail
  • rm -rf — Recursive force deletion command in Taskfile.yml
  • network request — Outbound network request in config.example.yaml
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Read-only Alertmanager intelligence agent — correlates alerts, triages incidents with LLMs, and exposes findings via MCP to AI coding agents

README.md

AlertINT

AlertINT

Infrastructure Alerts, Decoded

license release CI

AlertINT is a self-hosted, Fair Source agent runtime that turns infrastructure alerts into incident context your AI agent reads directly over MCP.

A single Go binary that sits between Alertmanager and your AI agent. It ingests alert webhooks, correlates them into incidents through an open rule engine, runs an LLM triage skill, posts structured findings to Slack, and exposes the resulting incident state — plus read-only Prometheus access — to any MCP client. Read-only by design. Local state. You bring the LLM key.

Full documentation: alertint.com/docs

Get started

The Quickstart is
the canonical walkthrough — install (single binary or bundled Docker Compose
stack), configure, and prove the whole pipeline with one command:

alertint drill --config config.yaml

The built-in incident drill plants a fake deploy, fires a burst of
clearly-marked synthetic alerts through the production ingress, and polls
until triage prints the finding — a causal analysis naming the planted
deploy. From zero to that finding takes about ten minutes; then connect an
MCP client to investigate it, and point Alertmanager at the agent for real
alerts.

How it works

flowchart LR
    AM[Alertmanager] -->|webhook| ING[Ingest + dedup]
    ING --> COR[Correlation<br/>rule engine]
    COR --> AI[AI synthesis<br/>Claude]
    AI --> SLK[Slack finding]
    COR --> MCP[MCP server]
    MCP --> AGT[Your AI agent<br/>investigation tools]

Documentation

The /docs folder in this repo is the canonical source for those pages — the website renders it at build time. Documentation PRs are welcome here; see docs/README.md and CONTRIBUTING.md.

License

AlertINT is Fair Source, licensed under FSL-1.1-ALv2 (Functional Source License). Free to read, use, modify, and self-host at any scale. The only restriction is offering the software to others as a competing commercial product or service. Each release converts to Apache 2.0 — full open source — two years after publication. See fsl.software for the license text.

Reviews (0)

No results found