{"slug": "i-built-a-self-hosted-ai-incident-diagnosis-tool-that-only-returns-a-root-cause", "title": "I Built a Self-Hosted AI Incident Diagnosis Tool That Only Returns a Root Cause When Multiple Diagnoses Agree", "summary": "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.", "body_md": "Most AI incident diagnosis tools will happily produce a root cause even when the evidence is weak. Argus takes a different approach.\n\nWhen 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.\n\nIt'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.\n\nI'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.\n\nGitHub: [https://github.com/k1ngalph0x/argus](https://github.com/k1ngalph0x/argus)\n\nI'd genuinely appreciate people trying it out and telling me where the design falls apart, what feels over-engineered, or what you'd change.", "url": "https://wpnews.pro/news/i-built-a-self-hosted-ai-incident-diagnosis-tool-that-only-returns-a-root-cause", "canonical_source": "https://dev.to/k1ngalph0x_107d1b7ec2377d/i-built-a-self-hosted-ai-incident-diagnosis-tool-that-only-returns-a-root-cause-when-multiple-4cfm", "published_at": "2026-07-14 18:29:28+00:00", "updated_at": "2026-07-14 18:59:37.418779+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "artificial-intelligence", "ai-infrastructure"], "entities": ["Argus", "Cloudflare", "Anthropic", "GitHub", "Prometheus", "OTLP"], "alternates": {"html": "https://wpnews.pro/news/i-built-a-self-hosted-ai-incident-diagnosis-tool-that-only-returns-a-root-cause", "markdown": "https://wpnews.pro/news/i-built-a-self-hosted-ai-incident-diagnosis-tool-that-only-returns-a-root-cause.md", "text": "https://wpnews.pro/news/i-built-a-self-hosted-ai-incident-diagnosis-tool-that-only-returns-a-root-cause.txt", "jsonld": "https://wpnews.pro/news/i-built-a-self-hosted-ai-incident-diagnosis-tool-that-only-returns-a-root-cause.jsonld"}}