AI agent sandboxing has become one of the hottest topics in cloud native computing. Every booth seems to offer a way to isolate agents. Yet not every sandbox offers the same protection or the same performance.
Cosmonic CTO Bailey Hayes examines that challenge with Mike Vizard at KubeCon + CloudNativeCon in Salt Lake City.
A Million Agents on One Pod
Hayes compiled popular agents such as Codex, Goose and Hermes to WebAssembly. Each agent runs in its own sandbox, and so does every tool it calls.
In a live demo, she ran a million agents on a single Kubernetes pod. Arm supplied a 64-core host for the test. CNCF wasmCloud scheduled the workloads and ran them in a multi-tenant host.
The compiled Codex agent weighed in at just 243 kilobytes. The bottleneck turned out to be session storage, not the host itself. The benchmark and its Ansible playbook are open source.
Deny by Default
Hayes sees two classes of agents emerging. General-purpose coding agents need broad resources. Single-purpose agents, like a support bot, should be locked down to a few tasks.
That is where capability-based security comes in. A WebAssembly component declares exactly what it imports and exports. Nothing else is allowed.
Hayes points to the NIST definition of a sandbox. It calls for isolation and deny-by-default controls. Most approaches deliver isolation, she says, but few deny by default. Effective AI agent sandboxing needs both, along with least privilege.
Building on Kubernetes
Hayes warns against reinventing Kubernetes for agentic workloads. Its RBAC, network policy and namespaces are there for good reasons.
wasmCloud uses an operator and custom resources that mirror a standard deployment. The operator pushes events to hosts over NATS instead of polling the Kubernetes API. That matters when workloads start in microseconds.
Cosmonic Desktop helps developers build for WebAssembly with an MCP server and templates. Cosmonic Control adds the high availability, service mesh and workload identity enterprises need.
Her advice for IT teams is simple. Join the community, because open source will solve this faster than any in-house effort.
Up Next in KubeCon 2026 Salt Lake City
-
Agent Sandboxing Finds a Neutral Home...
Agents Need Guardrails, Not Blame
Agent sandboxing is becoming a core requirement as AI agents run untrusted code at scale. Agents chase their mission with single-minded focus. That makes the box around them just as important as the instructions they receive.Google GKE Product Manager Nick Eber...
-
AI Coding Agents Move Into Isolated W...
AI coding agents are moving off developer laptops and into the enterprise. That shift raises hard questions for platform teams. Where do agents run? What can they reach? Who controls the data, and who pays for the tokens? Many organizations are also rethinking whether AI workloads belong in a hyp...
-
Data Management Should Build Down Fro...
Models Come and Go. Data Stays.
Agentic data management is quickly becoming one of the hardest problems in enterprise AI. Models can be rented, swapped and replaced each year. The data underneath them is where long-term value lives. Agents also generate far more queries than humans ever did. Mach...