Google Cloud Launches Agent Compute Engine: A MicroVM per AI Agent
Google Cloud has announced Agent Compute Engine, a compute service built specifically for AI agents.Google Agent Compute Engine gives each agent its own hardware-isolated microVM.The sandbox holds zero credentials.The service already powers Gemini as an agent for work tasks.
Google unveiled it this week at AGNTCon + MCPCon.Customer preview is targeted for the coming months.The pitch: VM-grade isolation with container-like speed and density.TL;DR Unit: One hardware-isolated microVM per agent session, with its own guest kernel, root access and Hyperdisk.
Runs on: Google-managed hosts using Titan silicon and the Titanium IPU.Open-source sibling Agent Substrate runs on any Kubernetes cluster.Performance: Idle agents are checkpointed to zero active resources and resumed from snapshots.Google gives no ACE boot or density numbers.
Best: Agent Substrate hit 500 activations/s at under 500 ms suspend/resume across 200,000 agents.Worst: No published boot time, density, pricing or preview date for Agent Compute Engine itself.What is Google Agent Compute Engine?
Agent Compute Engine is a Google Cloud service that runs each AI agent inside a dedicated microVM.Per the technical post, it powers Gemini, Antigravity, and internal evaluation and RL pipelines.Google splits every agent into 2 parts.The harness, or ‘brain,’ calls the model.
The sandbox, or ‘hands,’ runs code, shell commands and browsers.The harness runs fully outside the sandbox and dispatches explicit commands into it.How does the microVM isolation work?Each session runs in a single-tenant microVM behind a Cloud Hypervisor boundary.
Hosts are stateless appliances with a read-only root filesystem enforced by dm-verity.Titanium holds attestation keys outside the guest.The networking design is the unusual part: MicroVMs have no standard network interface, no default gateway and no direct VPC access.
All traffic crosses a virtio-vsock boundary to a local proxy, then to an external gateway.Guests get only a session-scoped SPIFFE certificate and a short-lived identity token.Agent Gateway swaps in the real backend credential in flight, after policy checks.
Google assumes an attacker controls everything inside the sandbox.A prompt-injected agent finds no secrets to steal.What are the Four Agent Identities?Google defines 4 identities for every agent workload: User identity: authenticates the overall task only.
Delegated on-behalf-of identity: a scoped grant stored in a central authorization service, never on the node.Agent Workload Identity: a short-lived SPIFFE identity, the only one used for sandbox traffic.Agent Workforce Identity: an agent’s own account and resources.
The workload identity is useless for direct API calls if exfiltrated.It only identifies which sandbox sent a packet.How does it keep idle agents cheap?Google team found agents spend most of their time waiting on models or users.So the sandbox signals when a tool call finishes.
The host checkpoints the idle microVM to zero active resources.It resumes on the next call.Density comes from copy-on-write memory sharing.Pre-warmed snapshot images are mapped with DAX, so microVMs on a host share base OS and library pages.Only each agent’s modified pages consume private memory.
Harnesses also get cloning, snapshot/forking, rewind and rollback.Storage is split 3 ways: disposable scratch overlays, shared read-only volumes, and persistent user workspaces on Hyperdisk.Harnessoutside
Sandbox microVMuntrusted
vsock + local proxyhost
Agent Gatewayoff-node
Token swapoff-node
BackendWorkspace / VPC Step 1 Back Next step Auto-play
Source: Google Cloud technical deep dive, Oct 22, 2026. State 1
Running tool call Code, shell or browser executes inside the microVM. State 2
"Thinking" signal Sandbox reports no commands or background tasks in flight. State 3
Checkpointed idle State preserved. Zero active host resources. State 4
Resume Next tool call restores the microVM from its snapshot. Copy-on-write memory, shared across 6 microVMs 1 shared copy of base OS, libraries and binaries (DAX + CoW)
<div class="l
Related
相關文章
SpaceX 與特斯拉擬合併:馬斯克想用一樁交易,把汽車、火箭和 AI 捏成同一個帝國
這樁交易到底有多大說服力,取決於你多大程度上相信馬斯克那個"去火星、傳播意識之光"的故事——他在本週的 SpaceX 財報電話會和更早的 S-1文件裡都這麼講。但剝開敘事外衣,真正驅動合併的,是明晃晃的財務邏輯和馬斯克本人日益膨脹的控制權胃口。
砸下 150 億美元!DeepSeek 攜手寧德時代轉戰內蒙古,1GW 國產智算中心掀起基建狂潮
DeepSeek 攜手寧德時代轉戰內蒙古,1GW 國產智算中心掀起基建狂潮發布於AI新閒資訊時間 :Oct 23, 2026閱讀 :1分鐘據 多家權威媒體報道,人工智能領域迎來了一筆備受矚目的鉅額投資。DeepSeek 近期正接近完成規模高達150億美元的新一輪融資,這筆資金的核心用途已明確鎖定——用於在內蒙古烏蘭察布市投資建設一塊規模達到1GW 的全新數據中心。
Hugging Face 推出 Carbon-X:基於千問,讓科學家"與 DNA 對話"
這是一個 140 億參數、用於 DNA 理解與生成的開放模型。它的玩法很新鮮——把 DNA 序列和自然語言揉進同一個模型。研究者能拿特定序列提問、預測突變影響,甚至生成新的 DNA 片段;它還能當"專業副手",幫別的模型讀懂原本看不透的基因。
火山引擎發佈Seedance2.54K:480P樣片打磨後生成4K正片
該版本通過專項訓練,更充分地學習人物表情、細微動作與畫面細節,是Seedance2.5這一代中最強的模型。產品支持Draft(樣片)模式,終端用戶可先用480P樣片快速驗證分鏡、反覆打磨鏡頭,確定滿意效果後再生成4K正片,以更優成本給足創意探索空間。
Gemini 4 Argon 首發 72 小時吞下 25 萬億 Token,皮查伊首談砍掉 3.5 Pro 內幕
即便是家底豐厚的谷歌,面對瞬間湧入的調用洪流,也不得不再次啟動算力限流。在科技播客《Sources》的最新訪談裡,谷歌 CEO 桑達爾·皮查伊覆盤了這次發佈的細節,也第一次把過去幾個月外界最困惑的幾件事攤開講清——那個曾在 I/O 大會上被點名的 Gemini3.
Etsy宣佈禁止平臺銷售AI生成食譜與手工圖樣
此舉旨在應對平臺日益嚴峻的信任危機,遏制AI生成內容對買賣雙方交易體驗的負面衝擊。當前,由於買家難以分辨商品中是否包含AI生成內容,該問題已演變為阻礙用戶活躍交易的核心障礙之一,同時誠實賣家也面臨著原創作品被誤導性AI商品稀釋的困境。為此,Etsy進一步收緊了規範,明確規定賣家必須展示根據說明製作出的未經修改的實物照片,並禁止通過機器人程序完全無人參與地自動生成商品刊登信息。