The agent platform that runs in your own cloud.

How it works

Connect your cloud. Point your agent at it.

Quome runs the control plane. The sandboxes, the compute, the network, the storage and the logs run inside your account. Any agent that can call a CLI or an API can use them.

• 01

  Connect your cloud, without handing over keys. Quome connects to your GCP, AWS or Azure project through Workload Identity Federation. No long-lived credentials are stored on our side; access is scoped, logged and revocable in seconds.

• 02

  Your agent asks for a sandbox. From Claude Code, a custom agent loop or a workflow, each request gets a fresh microVM in your VPC with the network policy you chose.

• 03

  The run ends. The box is gone. Code executes, results land in your bucket or database, and the VM is destroyed. Every command, egress attempt and secret access is in your audit log.

• Any agent, any harness

  Claude Code, the OpenAI Agents SDK, LangGraph, your own loop. If it can shell out or call an API, it can run in a Quome sandbox.

• Live preview URLs

  Every sandbox can expose a preview URL for the thing the agent built, behind your auth, inside your VPC.

• Model gateway and MCP

  An OpenAI-compatible gateway for Claude, GPT and Gemini plus MCP tools, so the agent inside the box reaches models without reaching the internet.

• Your data, your bucket

  Inputs and outputs stay in your storage and your database. Quome never stores your data.

What's inside the wall

Isolation you can show a CISO.

Every control below is on by default for every sandbox, unless marked Enterprise.

• MicroVM per run

  Hardware-isolated microVMs, not shared-kernel containers. One run, one VM, no neighbors.

  Default

• Network policy per sandbox

  Isolated, outbound or full. Isolated means no outbound path at all: there is no filter to tunnel through.

  Isolated by default

• Ephemeral by design

  Sandboxes carry a TTL and are destroyed when the run ends. Nothing persists unless the agent writes to your storage.

  Default

• Your VPC, your account

  Per-run VPC isolation inside your own GCP, AWS or Azure project. The blast radius is bounded by your policies, not a vendor's.

  Your cloud

• Zero stored credentials

  Workload Identity Federation end to end. Secrets are injected at runtime from your Secret Manager or Key Vault and revoked on exit.

  Default

• Customer-owned encryption

  AES-256-GCM with KMS keys you control. Dedicated database and cache per organization.

  Default

• Audit log for every run

  Commands, egress attempts, secret access and lifecycle events, written to logs you own.

  Default

• Scanned, signed supply chain

  Container scanning, SBOMs for every image, and SLSA Level 3 signing, so what runs in the box is what you approved.

  Default

• Compliance built in

  SOC 2 Type 1. HIPAA-aligned platform with a BAA on Enterprise for eligible services. MFA, WebAuthn and SSO. A pre-filled security questionnaire is ready for your review.

  Enterprise

Compare

Hosted sandbox APIs run in their cloud. Quome runs in yours.

The difference is not features. It is where the blast radius lives and whose name is on the security review.

Set up with you

We stand it up in your cloud.

You do not need a platform team to get this right. Our engineers and security experts deploy the sandbox plane into your account, integrate it with the agents you already run, and hand you the keys and the evidence.

1. 01

   Connect your cloud

   Workload Identity Federation. No keys handed over.

   You
2. 02

   Deploy the sandbox plane

   MicroVM pool, isolated VPC, KMS and audit sinks in your account.

   With you
3. 03

   Wire in your agents

   CLI and API integration with your harness, and network policies per workload.

   With you
4. 04

   Security review pack

   Architecture, shared-responsibility model and a pre-filled questionnaire.

   With you
5. 05

   You own it

   Your keys, your infrastructure, your logs. We operate the control plane.

   Yours

Pricing

One flat fee. Unlimited sandboxes.

Sandbox compute runs in your account at your cloud's published rates. Quome adds zero markup, and you keep your existing discounts.

Why trust us

We help write the standards agents get measured against.

• Core contributors to AISVS

  We help author the AI Security Verification Standard, the framework AI systems are measured against. We build to it because we help define it.

• Directing the Proof of Control standard

  We help direct the Advanced AI Society's Proof of Control standard: how AI systems prove they stay under human control. Sandboxing is where that proof starts.

• Healthcare AI Agents Task Force

  We created the Task Force for AI Agents in Healthcare, setting the bar for how agents are deployed safely in clinical settings.

• We come from enterprise

  Built by people who have shipped inside regulated enterprises. Quome is designed around the procurement, security-review and compliance walls we hit ourselves.

See the open research behind this work, and our subprocessors.

Questions

What security teams ask first.