OpenShell on Kubernetes: A guide for platform engineers

7.3 relevance

OpenShell on Kubernetes guide is highly actionable for platform engineers, directly relevant to AI agent infrastructure and cloud-native trends.

AI/ML cncf.io

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

For platform engineers running AI agents in production, OpenShell bridges the gap between Kubernetes' coarse network policies and the fine-grained, per-call controls needed to safely execute untrusted agent code that holds real credentials.

Key Takeaways

Evaluate OpenShell's Gateway API for agent sandboxing but watch for the upcoming Kubernetes CRD operator and scalable supervisor deployment options before committing to production.

OpenShell on Kubernetes: A guide for platform engineers

Summary

OpenShell, a CNCF Sandbox project from NVIDIA, provides a secure runtime for AI agents on Kubernetes by sandboxing each agent with Landlock filesystem limits, seccomp process restrictions, deny-by-default network rules, and credential placeholders swapped by a supervisor. Its Kubernetes backend uses the Agent Sandbox resource (agents.x-k8s.io) to map agents to standard Pods, Services, and NetworkPolicies, while the gateway enforces per-binary and per-method egress policies that Kubernetes NetworkPolicy alone cannot express. The demo stack runs on kind with Kubernetes 1.35, Cilium 1.20, and Kyverno 1.18.2, though sandbox creation currently requires the Gateway API (not the Kubernetes API) and the supervisor-per-agent model may not scale for large deployments.

Author

epower