{"slug": "the-next-chapter-for-red-hat-ai-agents-rewrite-the-cloud-native-playbook", "title": "The next chapter for Red Hat: AI agents rewrite the cloud-native playbook", "summary": "Red Hat LLC is bringing Kubernetes-native security to AI agents at KubeCon + CloudNativeCon North America in Salt Lake City, pairing OpenShift with Nvidia Corp.'s OpenShell runtime to sandbox agent execution and enforce policy on agent access. The llm-d project, which Red Hat backs, has reached version 1.0 with capabilities for serving the context-heavy workloads agents create. Red Hat principal AI community architect Pete Cheslock said OpenShell builds on Kubernetes infrastructure, with sandboxing limiting the damage an agent can cause rather than making it trustworthy.", "body_md": "### The next chapter for Red Hat: AI agents rewrite the cloud-native playbook\n\nRed 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 that can affect the business. The next phase of AI agent infrastructure requires enforceable security boundaries alongside efficient resource management.\n\nRed Hat arrives at [KubeCon + CloudNativeCon North America](https://www.thecube.net/events/linux-foundation/kubecon-cloudnativecon-na-2026) in Salt Lake City this week with a growing portfolio of technologies addressing those requirements. OpenShift provides the Kubernetes foundation; its work with Nvidia Corp. on OpenShell addresses agent execution and security; and the [llm-d project](https://siliconangle.com/2026/10/20/ibm-backed-llm-d-framework-adds-controls-for-running-ai-models-in-house/?utm_source=chatgpt.com) has reached version 1.0 with capabilities for serving the context-heavy workloads agents create. Together, these developments position Red Hat to help enterprises manage agentic AI through open, Kubernetes-based infrastructure.\n\nUnlike conventional applications, autonomous agents can generate commands, invoke tools and delegate work across multiple systems. That flexibility creates opportunities for automation while increasing the importance of consistent access controls and oversight.\n\n*This feature is part of SiliconANGLE Media’s exploration of how cloud-native infrastructure is evolving to support enterprise AI, with Red Hat and the broader Kubernetes ecosystem addressing the security, operational efficiency and scalability requirements of autonomous agents. (* Disclosure below.)*\n\n### Red Hat advances Kubernetes-native security for AI agents\n\nThe rapid adoption of OpenClaw has brought renewed attention to agent security. An agent that can read files, run shell commands and make network calls needs clearly defined permissions and isolation to operate safely within enterprise environments.\n\nRed Hat’s response centers on its collaboration with Nvidia around OpenShell, a runtime that places agents inside isolated execution environments and applies policy to their access. Nvidia developed OpenShell; Red Hat is working with Nvidia and the wider community to integrate the technology into Red Hat AI and its open hybrid cloud platform. Red Hat’s [announcement](https://siliconangle.com/2026/10/21/red-hat-and-nvidia-expand-their-partnership-to-secure-autonomous-ai-agents/?utm_source=chatgpt.com) describes the work as part of a broader effort to bring security-focused agentic AI capabilities to enterprise infrastructure.\n\nOpenShell uses sandboxing, process-aware policy and controls over network access and credentials. Red Hat has also described how OpenShell can work with OpenShift’s sandboxed containers, adding application-level restrictions inside a virtual-machine boundary. These complementary layers govern agent behavior and isolate the environments in which agents operate, as Red Hat explains in its [technical overview of layered sandboxing](https://developers.redhat.com/articles/2026/07/16/layered-sandboxing-ai-agents-openshift-and-openshell?utm_source=chatgpt.com).\n\nThe distinction matters because sandboxing does not make an agent trustworthy. It limits the damage an agent can cause when its instructions, generated code or external inputs lead it somewhere they should not.\n\nIn a recent [interview](https://siliconangle.com/2026/10/27/red-hat-openclaw-agents-kubeconna/?utm_source=chatgpt.com) with theCUBE, [Pete Cheslock](https://www.linkedin.com/in/petecheslock?utm_source=chatgpt.com), principal AI community architect at Red Hat, described how OpenShell builds on Kubernetes infrastructure: “The agent sandbox is one of them, so that you can deploy these agents in a secure way using Kubernetes native APIs.” His comments get to the central issue: enterprises cannot delegate authority to agents without defining and enforcing its limits.\n\nRed Hat Chief Technology Officer [Chris Wright](https://www.linkedin.com/in/chris-wright-b733851?utm_source=chatgpt.com) also emphasized the importance of agent isolation in a May [interview](https://siliconangle.com/2026/05/14/open-source-ai-trust-inference-red-hat-rhsummit/?utm_source=chatgpt.com) with theCUBE. Agents that can take real actions in a business need sandboxing and least-privilege protections, he explained. \n\n“You’ve got to give it the right sandboxing. You’ve got to put protections around the agent, give it least privileges so it doesn’t think about read versus read-write — very big difference,” Wright said in SiliconANGLE’s coverage of Red Hat Summit.\n\nBeyond sandboxing, enterprises must manage agent identities, data permissions, tool access and authorization. That distinction is reinforced by [Paul Nashawaty](https://www.linkedin.com/in/paulnashawaty?utm_source=chatgpt.com), practice lead and principal analyst for application development, modernization and cloud native at theCUBE Research, whose [September analysis](https://thecuberesearch.com/ai-agent-governance-is-moving-from-observability-to-provable-trust/) of AI agent governance examines the difference between observing what agents do and proving what they were authorized to do. The research identifies runtime enforcement, delegated authority and verifiable audit evidence as requirements that become more important as autonomous systems move into production.\n\n“This creates an opportunity for platforms that can unify application development, infrastructure orchestration, security and observability rather than adding another layer of disconnected tooling,” Nashawaty said.\n\n### Red Hat’s llm-d extends Kubernetes infrastructure for AI inference\n\nBeyond security, agents create new requirements for inference infrastructure. An agent may call a model, retrieve information, invoke a tool and return to the model with additional context. Each interaction consumes compute, memory and network capacity, while the system must preserve enough context to continue efficiently.\n\nRed Hat’s llm-d project addresses part of that problem. Founded by Red Hat, IBM Corp., Google Cloud, CoreWeave Inc. and Nvidia, and now governed by the Cloud Native Computing Foundation, llm-d uses Kubernetes-native components to distribute inference across accelerators and manage traffic between them.\n\nThe project reached version 1.0 on Oct. 20, adding session-aware routing, turn-priority scheduling, multi-tenant quality-of-service controls and high-availability operations. Those features aim to keep multi-turn requests close to cached context, prioritize latency-sensitive work and reduce disruption during maintenance. The [Red Hat release announcement](https://www.redhat.com/en/about/press-releases/llm-d-1-advances-open-cost-efficient-ai-inference-production-scale?utm_source=chatgpt.com) and [Google Cloud’s technical overview](https://cloud.google.com/blog/topics/ai-infrastructure/llm-d-1-0-an-open-source-stack-for-distributed-inference?utm_source=chatgpt.com) describe the release.\n\nThe architecture provides operators with additional options for coordinating inference workloads and managing accelerator resources within Kubernetes.\n\nRed Hat Senior Vice President and AI Chief Technology Officer [Brian Stevens](https://www.linkedin.com/in/brianstevens?utm_source=chatgpt.com) described one of llm-d’s central architectural decisions in [SiliconANGLE’s report on Kubernetes inference](https://siliconangle.com/2026/03/24/red-hat-bets-big-kubernetes-inference-llm-d-kubeconeu/?utm_source=chatgpt.com): “We can independently scale the processing of the input from the production of the tokens.”\n\nOther infrastructure providers are addressing complementary requirements. ScaleOps Labs Ltd. focuses on GPU utilization and resource optimization across Kubernetes workloads. Vultr Holdings LLC offers GPU infrastructure and Kubernetes-based model deployment, while Broadcom Inc. positions VMware Cloud Foundation as a private-cloud platform for Kubernetes and AI workloads. Together, these offerings reflect expanding enterprise choices for resource optimization, accelerator capacity and private-cloud operations.\n\nThe operational gap appears in theCUBE Research’s [“Day 0 Build, Test Survey Research Report.”](https://thecuberesearch.com/scaling-cloud-native-applications-with-ci-cd-ai-and-secure-developer-tooling/) Based on a survey of 375 IT, development, operations and platform engineering professionals, the research found that cloud-native adoption is widespread but maturity remains uneven. Inconsistent automated testing, fragmented developer tools and gaps in rollback capabilities continue to complicate production deployment.\n\n“Ninety-two percent of organizations are integrating AI into at least one stage of the software development lifecycle, while 79% expect full-scale AI agent adoption within the next three years,” Nashawaty said, adding that approximately 30% still face operational readiness challenges.\n\nThe broader industry is also moving toward production-scale infrastructure. The [CNCF’s 2026 annual cloud-native survey](https://www.cncf.io/reports/the-cncf-annual-cloud-native-survey/?utm_source=chatgpt.com) found that 82% of container users run Kubernetes in production and that 66% of organizations hosting generative AI workloads use Kubernetes for some or all inference. Those figures reinforce Kubernetes’ expanding role as enterprises adopt AI workloads.\n\n### Open-source collaboration expands Red Hat’s AI infrastructure opportunities\n\nThe open-source ecosystem is expanding alongside agentic AI adoption. On Nov. 5, Google announced the donation of Agent Substrate, gVisor and OpenRL to the CNCF following their acceptance into its Sandbox program in October. The projects address agent execution, isolation and reinforcement-learning workflows. Agent Substrate separates agent sessions and identities from active compute, allowing idle environments to pause and resume; gVisor provides an additional isolation boundary for untrusted code; and OpenRL supports reinforcement-learning post-training on Kubernetes. Google’s [announcement](https://cloud.google.com/blog/products/containers-kubernetes/open-infrastructure-for-autonomous-agents-comes-to-cncf?utm_source=chatgpt.com) describes the projects and their transition into CNCF governance.\n\nThese contributions complement broader efforts across the Kubernetes community. Red Hat is a co-founder of llm-d and is integrating Nvidia’s OpenShell into its enterprise AI platform, while Google is contributing technologies related to runtime and training requirements. The common emphasis on open infrastructure creates opportunities for interoperability as enterprise AI systems mature.\n\nBroadcom added another development on Nov. 9, announcing that its [VM API project](https://investors.broadcom.com/news-releases/news-release-details/broadcom-contributes-vm-api-open-source-project-cloud-native) had been accepted into the CNCF Sandbox. The project aims to let organizations manage virtual machines through Kubernetes application programming interfaces across different infrastructure providers. This extends the Kubernetes conversation to managing virtual machines alongside containerized workloads.\n\n[Project Lightwell](https://newsroom.ibm.com/2026-05-28-ibm-and-red-hat-commit-5-billion-to-redefine-the-future-of-open-source-in-the-ai-era) adds another dimension to Red Hat’s enterprise strategy. Announced with IBM in May, the $5 billion initiative aims to use AI-assisted vulnerability identification and validated fixes to strengthen open-source software supply chains. The initiative extends security efforts to the software dependencies supporting production workloads.\n\n[Sam Weston](https://www.linkedin.com/in/skweston?utm_source=chatgpt.com), industry analyst for enterprise applications, development and modernization at theCUBE Research, points to the infrastructure mix enterprises already operate.\n\n“With our data showing 61.8% of enterprises run hybrid deployments and an additional 10% operate across multi-cloud environments, Red Hat’s hybrid-first platform strategy aligns closely with where enterprise infrastructure lives today,” Weston said.\n\nRed Hat’s established OpenShift footprint provides a foundation for connecting these developments. As enterprises deploy more autonomous workloads, the company is positioned to combine Kubernetes orchestration, agent isolation and distributed inference within its broader hybrid cloud strategy.\n\nThe opportunity extends beyond any individual project. OpenShift, llm-d and OpenShell illustrate how Red Hat is contributing to an open infrastructure model that accommodates both conventional applications and emerging AI agents.\n\nFor enterprises, the objective is to make AI workloads secure, efficient and manageable without losing control over how autonomous systems operate. Red Hat’s work across the Kubernetes ecosystem reflects how that foundation is taking shape.\n\n*(* Disclosure: Red Hat is a sponsor of theCUBE’s KubeCon + CloudNativeCon NA coverage. Neither Red Hat nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)*\n\n##### Image: SiliconANGLE/ChatGPT\n\n# A message from John Furrier, co-founder of SiliconANGLE:\n\nSupport our mission to keep content open and free by engaging with theCUBE community. **Join theCUBE’s Alumni Trust Network**, where technology leaders connect, share intelligence and create opportunities.\n\n- **15M+ viewers of theCUBE videos** , powering conversations across AI, cloud, cybersecurity and more\n- **11.4k+ theCUBE alumni** — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network\n\n### Are you an AWS customer?  Support SiliconANGLE financially by buying your AWS services from our Marketplace portal page and links: [https://siliconangle.com/aws-marketplace/](https://siliconangle.com/aws-marketplace/)\n\n##### **About SiliconANGLE Media**\n\n[SiliconANGLE](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fsiliconangle.com%2F&esheet=54119777&newsitemid=20240910506833&lan=en-US&anchor=SiliconANGLE&index=9&md5=646b1b564e2259100a2b8638aab0a552),\n\n[theCUBE Network](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fwww.thecube.net%2F&esheet=54119777&newsitemid=20240910506833&lan=en-US&anchor=theCUBE+Network&index=10&md5=7de2a85f95ab4a4a495cede20b8cb1da),\n\n[theCUBE Research](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fthecuberesearch.com%2F&esheet=54119777&newsitemid=20240910506833&lan=en-US&anchor=theCUBE+Research&index=11&md5=7bb33676722925eb57d588ec343e4f6f),\n\n[CUBE365](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fwww.cube365.net%2F&esheet=54119777&newsitemid=20240910506833&lan=en-US&anchor=CUBE365&index=12&md5=d310fb35919714e66ad8d42c9c0c1bc6),\n\n[theCUBE AI](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fwww.thecubeai.com%2F&esheet=54119777&newsitemid=20240910506833&lan=en-US&anchor=theCUBE+AI&index=13&md5=b8b98472f8071b23ebb10ab9a8dd0683)and theCUBE SuperStudios — with flagship locations in Silicon Valley and the New York Stock Exchange — SiliconANGLE Media operates at the intersection of media, technology and AI.\n\nFounded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.", "url": "https://wpnews.pro/news/the-next-chapter-for-red-hat-ai-agents-rewrite-the-cloud-native-playbook", "canonical_source": "https://siliconangle.com/2026/11/10/red-hat-ai-agent-infrastructure-kubeconna/", "published_at": "2026-11-10 15:49:10+00:00", "updated_at": "2026-11-10 15:51:53.734114+00:00", "lang": "en", "topics": ["ai-agents", "ai-infrastructure", "ai-safety", "artificial-intelligence"], "entities": ["Red Hat LLC", "Nvidia Corp.", "OpenShell", "OpenShift", "llm-d", "KubeCon + CloudNativeCon North America", "Pete Cheslock", "OpenClaw"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/the-next-chapter-for-red-hat-ai-agents-rewrite-the-cloud-native-playbook", "markdown": "https://wpnews.pro/news/the-next-chapter-for-red-hat-ai-agents-rewrite-the-cloud-native-playbook.md", "text": "https://wpnews.pro/news/the-next-chapter-for-red-hat-ai-agents-rewrite-the-cloud-native-playbook.txt", "jsonld": "https://wpnews.pro/news/the-next-chapter-for-red-hat-ai-agents-rewrite-the-cloud-native-playbook.jsonld"}}