{
  "id": 11818,
  "url": "https://thenewstack.io/self-healing-gpu-nodes",
  "title": "Self-healing GPU nodes in Kubernetes: What we learned building the EKS node monitoring agent",
  "summary": "When you run Kubernetes at the scale we do on Amazon EKS, nodes break constantly. GPUs fall off the PCIe The post Self-healing GPU nodes in Kubernetes: What we learned building the EKS node monitoring agent appeared first on The New Stack .",
  "authors": "Sajjan Gundapuneedi",
  "category": "news",
  "topics": "agents-autonomy",
  "orgs": "amazon",
  "regions": null,
  "published_at": "2026-07-19T13:00:00.000Z",
  "fetched_at": "2026-07-20T05:10:09.534Z",
  "source_slug": "x-the-new-stack-ai",
  "source_name": "The New Stack AI",
  "source_homepage": "https://thenewstack.io/ai/",
  "ethics_ai_record_url": "https://ethics.ai/record/11818",
  "original_url": "https://thenewstack.io/self-healing-gpu-nodes",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}