I Built a Self-Hosted AI Incident Diagnosis Tool That Only Returns a Root Cause When Multiple Diagnoses Agree

A developer built Argus, a self-hosted AI incident diagnosis tool that runs five independent diagnoses against an incident window and only returns a root cause when they converge. The tool is a single Go binary that ingests OTLP or Prometheus telemetry and uses an in-process event bus, requiring only an Anthropic API key. It has been validated on synthetic cases and reconstructed postmortems but seeks feedback from real-world production use.

Most AI incident diagnosis tools will happily produce a root cause even when the evidence is weak. Argus takes a different approach. When an anomaly fires, Argus runs five independent diagnoses against the same incident window. If they converge on the same root cause, it returns a confident diagnosis. If they don't, it returns novel instead of pretending it knows the answer. It's a single Go binary. The first version had Kafka, microservices, and two databases. It looked impressive on paper, but nobody would actually run it. I tore it down into a single process and replaced Kafka with an in-process event bus. Run it with docker run, bring your own Anthropic API key, and your telemetry never leaves the box. It ingests OTLP or Prometheus remote write; point your telemetry to a single endpoint. I've validated it on synthetic cases, reconstructed real postmortems Cloudflare 2019/2022 , and my own distributed system. It hasn't yet been tested against messy real-world production telemetry, which is exactly the kind of feedback I'm looking for. GitHub: https://github.com/k1ngalph0x/argus https://github.com/k1ngalph0x/argus I'd genuinely appreciate people trying it out and telling me where the design falls apart, what feels over-engineered, or what you'd change.