proomt

Search

Search posts, papers, and topics

All posts

Google Cloud BlogZongyun Hu5 min readintermediate

For SeaVerse, GKE Agent Sandbox reduces infrastructure costs by 60%

Read on google.com

Summary

SeaVerse uses GKE Agent Sandbox (Kata Containers + Cloudhypervisor or gVisor) to run isolated AI sandboxes at scale, achieving 300 allocations / s per cluster (90% ≤ 200 ms) and cutting infrastructure spend by up to 60% via flexible VM sizing and per‑sandbox persistent storage, while gaining native Cloud observability.

  • GKE Agent Sandbox provides kernel‑level isolation (microVM or gVisor) with the same Kubernetes scheduling model.
  • SeaVerse can allocate up to 300 sandboxes per second per cluster, with 90% of allocations completing in ≤200 ms.
  • Native Cloud Logging and Monitoring expose runtime metrics inside sandboxes, improving debugging.
  • Flexible VM sizing and per‑sandbox persistent disks enable cost reductions of up to 60% versus prior fixed‑type servers.

Running multi‑tenant AI workloads requires strong isolation without sacrificing latency; GKE Agent Sandbox shows a managed path to achieve that while also delivering measurable cost savings and observability, a pattern other AI‑heavy SaaS platforms can adopt.

5/10
observabilitysecuritykubernetesgkeagent sandboxcost

Related reading

  1. Agent Substrate brings high-density, scalable, trusted infrastructure to GKE

    Agent Substrate is an open‑source runtime for AI agents that runs on GKE. It uses Cloud Hypervisor microVMs or gVisor sandboxes to give kernel‑level isolation, a custom control‑ and data‑plane that can suspend/resume agents in <500 ms, and a “zero‑idle” model that packs >1 000 dormant agents per host (≈10× density vs. containers). GKE integration adds custom ComputeClasses, spot/on‑demand pools,…

    Google Cloud Bloggoogle.com6 min

  2. Introducing Filestore agent volumes: fully managed storage for agent workspaces

    Google Cloud adds Filestore agent volumes, a fully‑managed, elastic file‑system that automatically provisions isolated POSIX workspaces for GKE‑based AI agent sandboxes. Volumes attach in milliseconds, support RWX with file‑level locking, and charge only for used capacity with automatic tiering, aiming to cut cold‑start latency and storage waste for large‑scale agent fleets.

    Google Cloud Bloggoogle.com4 min

  5. Cloudflare Introduces the Agent Development Lifecycle to Replace Traditional SDLC

    Cloudflare’s Agent Development Lifecycle (ADLC) replaces the classic SDLC with an autonomous, event‑driven workflow system that lets AI agents handle code generation, testing, deployment, and maintenance. The platform builds on Cloudflare Workflows and the new @cloudflare/ci library to spin up containers, run headless browsers, and chain steps with caching and credential support. Observability is…

    InfoQinfoq.com2 min

  6. Accelerating the borderless Lakehouse: Announcing preview of cross-cloud caching

    Google Cloud previewed cross‑cloud caching for its Borderless Lakehouse. The feature caches sub‑file Parquet blocks in Google Cloud, encrypts them with GMEK, isolates cache per tenant/region, and validates freshness via metadata checks. In tests it can reduce cross‑cloud data transfer to <5% of the original size, lowering query latency and cost for Iceberg tables stored in other clouds. BigQuery…

    Google Cloud Bloggoogle.com3 minrelease