{
  "id": 19355165,
  "title": "The next chapter for Red Hat: AI agents rewrite the cloud-native playbook",
  "url": "https://urgent.news/2026/11/10/the-next-chapter-for-red-hat-ai-agents-rewrite-the-cloud-native",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-10T15:49:10.000Z",
  "source": {
    "name": "SiliconANGLE",
    "slug": "siliconangle",
    "url": "https://siliconangle.com/2026/11/10/red-hat-ai-agent-infrastructure-kubeconna/"
  },
  "original_language": "en",
  "account": "Red Hat LLC, a company specializing in Kubernetes management for enterprises, is extending its expertise to AI agents in production environments. These AI agents perform tasks that can impact business operations, such as executing commands, accessing external tools, and interacting with enterprise systems. To ensure secure and efficient deployment of these agents, Red Hat is unveiling a suite of technologies at KubeCon + CloudNativeCon North America in Salt Lake City.\n\nOpenShift, Red Hat's Kubernetes foundation, provides the necessary infrastructure. Nvidia's OpenShell, developed in collaboration with Red Hat, offers isolation for agent execution and enforces security policies. The llm-d project, now at version 1.0, serves the context-heavy workloads generated by these agents.\n\nThese developments position Red Hat to help enterprises manage AI agents using open, Kubernetes-based infrastructure. The company's response to the increased security concerns surrounding AI agents revolves around OpenShell, which isolates agents within execution environments and applies policies to their access. Additionally, Red Hat integrates OpenShell with its open hybrid cloud platform, enhancing security-focused agentic AI capabilities.\n\nRed Hat's layered sandboxing approach combines sandboxed containers with application-level restrictions, providing comprehensive isolation for agents. This ensures that agents operate within controlled environments, minimizing potential damage caused by erroneous instructions or inputs. Red Hat Chief Technology Officer Chris Wright emphasizes the importance of sandboxing and least-privilege protections for agents performing real actions within businesses.\n\nMoreover, managing agent identities, data permissions, tool access, and authorization are crucial aspects of deploying AI agents securely. Red Hat's llm-d project addresses the inference infrastructure requirements of agents by distributing inference across accelerators and managing traffic between them. The project, governed by the Cloud Native Computing Foundation, has reached version 1.0, incorporating features like session-aware routing, turn-priority scheduling, multi-tenant quality-of-service controls, and high-availability operations.",
  "summary": "Red Hat LLC has spent years making Kubernetes manageable for enterprises that would rather run applications than tend clusters. As AI agents move into production, the company is extending that experience to a new generation of workloads. AI agents don’t just consume infrastructure. They execute commands, call external tools, access enterprise systems and take actions […] The post The next chapter…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}