Isorun
$19.36 a month*
Home / AI agent sandboxes / Kubernetes Agent Sandbox
Kubernetes controller for stateful agent sandboxes with warm pools; offered on GKE at no extra charge.
Verdict (2026-11-13): Kubernetes Agent Sandbox scores 54/100, #54 of 63 AI agent sandboxes. Strong on free tier, docs and SDKs. Weak on limits. Best for: Teams already running Kubernetes that want a standard API for per-agent sandboxes.
Skip it if: Plain pods share the host kernel; you must configure gVisor, Kata or another runtime for untrusted code.
Prices checked 2026-11-15.
Agent Sandbox is a Kubernetes SIG Apps project that adds a Sandbox custom resource and controller for long-running, stateful single-pod workloads with a stable identity and persistent storage. Extensions add templates, claims and pre-warmed pools for fast allocation, plus Go and Python SDKs and an optional router. It orchestrates pods and leaves kernel isolation to a runtime class such as gVisor or Kata Containers. Google offers it on GKE at no extra charge beyond normal GKE resource pricing.
54/100 in AI agent sandboxes, rank 54 of 63. Parts with no data are left out and the rest is rescaled.
Full Kubernetes Agent Sandbox pricing: plans and costs at four workloads →
$19.36 a month*
$11.73 a month*
$10.14 a month*
$19.00 a month*
$17.95 a month*
$28.44 a month*
$20.00 a month*
$20.00 a month*
Kubernetes Agent Sandbox is not in the public benchmarks we track yet. See all benchmarks.
| Kubernetes Agent Sandbox | |
|---|---|
| Category | agent sandbox |
| Our score | 54/100 |
| Isolation | Kubernetes pod per sandbox; stronger isolation comes from a RuntimeClass such as gVisor or Kata Containers (GKE uses gVisor or microVMs) |
| Billing | Not applicable: free software run on your own cluster |
| Free tier | Free open-source software under Apache-2.0. On GKE it is offered at no extra charge; normal GKE pricing applies to the resources you create. |
| Pause and resume | Yes |
| GPU | Yes |
| Custom images | Yes |
| Open source | Yes (Apache-2.0) |
| Self-host | Yes |
| SDKs and interfaces | Go, Python, Kubernetes API (kubectl/YAML) |
| Regions | Any Kubernetes 1.25+ cluster you run (1.29+ recommended), including GKE. |
| Facts checked | 2026-11-13 |
No reviews yet. Have you used Kubernetes Agent Sandbox? Your review helps other developers choose.
Kubernetes Agent Sandbox scores 54/100, #54 of 63 AI agent sandboxes. Strong on free tier, docs and SDKs. Weak on limits. Best for: Teams already running Kubernetes that want a standard API for per-agent sandboxes. Facts checked 2026-11-13.
Free open-source software under Apache-2.0. On GKE it is offered at no extra charge; normal GKE pricing applies to the resources you create.
Kubernetes pod per sandbox; stronger isolation comes from a RuntimeClass such as gVisor or Kata Containers (GKE uses gVisor or microVMs).
In AI agent sandboxes, the top-rated are Isorun (78/100), Northflank (78/100), Koyeb Sandboxes (76/100). Kubernetes Agent Sandbox is #54 of 63.
It delegates low-level container isolation to secure "Sandbox Runtimes" (like gVisor or Kata Containers)
The Sandbox controller manages the lifecycle of the pod, including creation, scheduled deletion, pausing and resuming.
Agent Sandbox requires Kubernetes 1.25 or later
Agent Sandbox on GKE is open source software that you can use at no extra charge.
If you don't specify a GKE Sandbox runtime (gVisor or microVMs), your Pods run without kernel isolation, so don't use them to run untrusted code.
Use Agent Sandbox on GKE when each agent needs a dedicated Pod, GPUs or TPUs, a full Kubernetes PodSpec, or a GKE Autopilot cluster.
v1.0.11