{"resourceId":"redhat-ai-factory-nvidia-openshell-agent-security-reference-architecture-20261021","versions":[{"version":"external-2b5695e6d7c6d3ec839d6cac5bd1318f71861d3cfc0cc0cb97f6aebd3d038535","resource":{"id":"redhat-ai-factory-nvidia-openshell-agent-security-reference-architecture-20261021","title":"Red Hat AI Factory with NVIDIA accelerates agentic AI security capabilities across the open hybrid cloud","organization":"Red Hat (with NVIDIA)","sector":"Strategic partner platform: agent runtime security and governed inference","geography":"Global (vendor announcement; no SLED deployment named)","publishedAt":"Red Hat press release, Oct. 21, 2026","publicationDate":"2026-10-21","eventDate":"2026-10-21","sourceName":"Red Hat newsroom","sourceLabel":"Red Hat AI Factory with NVIDIA Accelerates Agentic AI Security Capabilities Across the Open Hybrid Cloud","sourceUrl":"https://www.redhat.com/en/about/press-releases/red-hat-ai-factory-nvidia-accelerates-agentic-ai-security-capabilities-across-open-hybrid-cloud","evidenceClass":"vendor-claim","outcomeClass":"emerging","topics":["developers-agents","data-security","infrastructure"],"finding":"Vendor claim: Red Hat says it is working with NVIDIA on the OpenShell Reference Architecture, an open-source agent sandbox runtime, and is actively collaborating to integrate it into Red Hat AI and Red Hat AI Factory with NVIDIA as a native platform capability. The release also describes a joint inference reference design with Model-as-a-Service access control, an AI gateway, vLLM and llm-d, plus self-service model discovery, rate limiting and entitlement tracking. The integration is described as in progress. The release gives no general-availability date, customer deployments or performance measurements.","sledRelevance":"Relevant to state CIO offices, university research IT and large county IT shops that are being asked to host AI agents on-premises or in a sovereign hybrid cloud. Per-tenant model access control, rate limiting and showback match how shared-service IT organizations charge back agencies or departments. No SLED customer is named, so applicability is inferred.","evidence":"Read the full press release on redhat.com. It is a forward-looking vendor announcement with a forward-looking-statements disclaimer. No benchmark, test method, sample or customer outcome is reported. The NVIDIA hardware claim that Vera CPUs deliver 2X faster agentic CPU performance comes from NVIDIA and gives no baseline.","architectureImplications":"Agent execution would move into a sandbox runtime enforced outside the agent process, sitting beside OpenShift AI model serving (vLLM/llm-d) and an AI gateway for model access. Agencies planning agent pilots on OpenShift should keep the sandbox, the gateway and model serving as separate layers.","governanceImplications":"Centralized MaaS access control and entitlement tracking could support agency-level usage policies and chargeback. Because the capability is not yet native, governance cannot rely on it today.","securityPrivacyImplications":"The stated principle is that agent controls belong in the runtime and infrastructure, not inside the agent. An independent source review in this edition finds the OpenShell enforcement design sound but several defaults permissive.","caveats":"Vendor announcement only. The OpenShell integration is not yet a shipping native capability, no SLED deployment is cited, and performance claims have no independent validation.","streamIds":["red-hat"],"roles":{"sales":"Sales framing: this is a roadmap conversation, not a proof point. Red Hat and NVIDIA are pitching agent safety as a platform layer (OpenShell sandboxing plus a governed model gateway) for customers who want agents on their own infrastructure. In SLED, it fits central IT teams that already run OpenShift and are being asked to host agent pilots for agencies or faculty. Keep the pitch bounded. Integration is still in progress, so position a design workshop and a controlled pilot, not production agent hosting.","engineering":"Engineering framing: treat the reference architecture as three layers. The agent sandbox (OpenShell) enforces filesystem, syscall and egress policy outside the agent. The AI gateway with MaaS handles model access, rate limits and entitlements. vLLM and llm-d serve the models. Check which pieces ship today on the customer's OpenShift AI version and which are still being integrated. Validate egress enforcement on the customer's actual CNI, and test credential injection, before any agent touches production systems.","delivery":"Delivery framing: an agent-hosting pilot on Red Hat AI needs explicit ownership of sandbox policy, gateway entitlements and model-serving upgrades. Plan a staged rollout: a sandboxed agent with no production credentials, then read-only access to one system of record, then limited writes with approval gates. Policy changes should go through change control. Pilot scope must not depend on the native OpenShell integration until Red Hat ships it."},"roleDetails":{"sales":{"customerProblem":"Central IT is asked to host AI agents for agencies or departments but lacks a governed way to stop agents from reaching systems and credentials they should not touch.","stakeholders":["State or university CIO/CTO","CISO","Platform engineering lead","Agency or departmental AI program owners"],"discoveryQuestions":["Which agent use cases are being requested, and which systems would they touch?","Do you already run OpenShift and OpenShift AI, and on which version?","How do you currently meter and charge back shared AI model usage?","What approval is required before an agent can write to a system of record?"],"valueHypothesis":"A single platform layer for agent sandboxing and model access control could reduce one-off security reviews for each agent pilot, if the integration ships as described.","potentialEngagement":"Agent-hosting architecture workshop plus a sandboxed, non-production agent pilot on existing OpenShift AI.","unsupportedClaims":["That OpenShell is a shipping, supported Red Hat AI feature today","Any performance or cost savings from the NVIDIA hardware claims","That the architecture satisfies a specific state security standard or CJIS/HIPAA requirement"]},"engineering":{"fit":"Fits customers with OpenShift-based AI serving who want on-premises or hybrid agent execution with external policy enforcement.","architectureIntegration":"OpenShell sandbox pods on OpenShift for agent execution; AI gateway and MaaS for model access and quotas; vLLM/llm-d for inference; NVIDIA GPU operator underneath.","prerequisites":["Current OpenShift AI release with MaaS/gateway components","CNI that enforces Kubernetes NetworkPolicy","GPU capacity and NVIDIA operator","Identity integration for per-tenant entitlements"],"constraints":["OpenShell integration described as in progress, not native today","No published performance data","Hardware claims tied to upcoming NVIDIA platforms"],"security":"Enforcement outside the agent is the intended model. Verify sandbox defaults, egress enforcement and credential handling independently, because the release offers no test evidence.","proofOfValue":["Demonstrate that a sandboxed agent cannot reach an unapproved endpoint on the customer's cluster","Demonstrate per-tenant rate limits and usage showback through the gateway","Confirm which components are GA versus preview on the customer's subscription"]},"delivery":{"work":"Stand up a sandboxed agent pilot environment, gateway entitlements and model serving, with documented policies and change control.","dependencies":["OpenShift AI version supporting the gateway features","Red Hat roadmap delivery of OpenShell integration","Security team policy review"],"ownership":"Central platform engineering team, with the CISO office owning sandbox and egress policy approval.","skillsAdoption":"Train platform engineers on agent sandbox policy authoring, gateway entitlement management and vLLM serving operations.","governanceCheckpoints":["Security review of sandbox policy before first agent run","Approval gate before an agent gets write access to any system","Quarterly review of model entitlements and usage"],"acceptanceCriteria":["Proposed: 100% of egress attempts to non-allowlisted hosts blocked in pilot tests","Proposed: per-tenant usage reports produced monthly","Proposed: no production credentials present in the agent environment"],"risks":["Roadmap slip leaves the pilot dependent on unsupported components","Permissive default policies left unchanged","Agent scope creep before governance is in place"]}},"retrievedAt":"2026-10-30T03:09:23Z","enrichedAt":"2026-10-30T03:21:15Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Platform teams would need Kubernetes, policy-as-code and agent-sandbox skills. The release does not address end-user accessibility.","procurementImplications":"Components are offered through partners including Cisco, Dell Technologies and Lenovo, so state contract vehicles for those OEMs may be the purchase path. Buyers should separate shipping features from roadmap items in solicitations.","operatingModelImplications":"Positions Red Hat AI as a shared internal AI service with per-tenant metering, which suits central IT acting as a service provider to agencies or colleges.","sourceVerification":{"openedUrl":"https://www.redhat.com/en/about/press-releases/red-hat-ai-factory-nvidia-accelerates-agentic-ai-security-capabilities-across-open-hybrid-cloud","referenceExcerpt":"Red Hat is actively collaborating with NVIDIA and the community to integrate the OpenShell Reference Architecture into Red Hat AI","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}