An open-source AI SRE agent
you host yourself.
When an alert fires, stromboli gathers the context, tells you how to stop the bleeding, then finds the root cause, and posts all of it to Slack.
$ brew install openstatushq/stromboli/stromboli// what it does
Mitigation first
It proposes a concrete fix (rollback, restart, scale up…) within a few tool calls, before it digs for the root cause.
Then the root cause
It tests hypotheses against your logs, metrics and deploys, and writes a structured report.
Read-only by default
It suggests and never acts on its own. The one opt-in exception: Fly.io machine actions a named human approves.
Any LLM
Claude by default; OpenAI, Gemini, DeepSeek, Ollama, OpenRouter or Vercel AI Gateway work too.
No data ingestion
Logs and metrics are queried on demand where they already live. Only the evidence each investigation used is stored.
Yours to host
One Go binary and a Postgres database. Docker Compose, Railway or Fly.io in one command. MIT licensed.
// how an investigation works
alertAlertmanager, Grafana, openstatus or any webhook fires.
briefIt gathers logs, metrics, deploys and the service catalog. No LLM yet.
mitigateIt posts how to stop the bleeding to Slack, fast.
investigateIt tests hypotheses and posts the root cause in the thread.
More in the life of an investigation.
// quickstart
cp .env.example .env # STROMBOLI_SECRET_KEY, STROMBOLI_API_TOKEN, ANTHROPIC_API_KEY...
docker compose up -d # stromboli + Postgres on http://localhost:8080
stromboli connector add loki loki url=http://loki:3100
stromboli catalog discover loki
stromboli investigate api --description "5xx on /v1/monitors"