Sandboxes · inside layer 02
coming

A sealed box for every run.

An agent that can run code and touch files needs somewhere safe to do it. Sandboxes will give every run its own isolated machine — real tools inside, torn down clean when the work is done — provisioned out of the capacity already sitting inside your perimeter.

sandbox · planned
provisioned on your ground
What a sandbox is[01/03]

An isolated place to do the work.

Today you hand an agent a machine you built and hope it cleans up after itself. The sandbox will make that part of the deployment — a fresh environment per run, with everything the agent needs inside and nothing else of yours reachable from it.

SB-01

One box per run

Every agent run will get a working space of its own — isolated from every other run, from your production systems, and from us. What an agent does inside its box stays inside its box.

SB-02

Real tools inside

A shell, a filesystem, packages, room to write and read and try again. Somewhere an agent can actually do work — not a stubbed environment that fails the moment the task gets real.

SB-03

Sealed and ephemeral

The box opens for the run and closes when it is done: torn down clean, nothing left behind, nothing carried into the next job. No long-lived environments to patch, no stray state to audit.

SB-04

Cut from your own capacity

The sandbox will be provisioned inside the deployment you already approved — your hardware, your network, your storage. An agent that can touch internal systems is doing it from inside, not through a tunnel out.

Where it sits[02/03]

Inside the runtime. On ground that already runs.

Sandboxes are one piece of the agent runtime — Layer 02 — which stands on the inference layer deployed and serving inside your boundary today. When your agents get a box, it will not be floating on something new.

Build it with us[03/03]

Tell us what your agents need to reach.

What a sandbox has to contain depends entirely on the work — which runtimes, which packages, which internal systems it must reach from inside. Those constraints are what we are designing against now.

Deployments start with inference — the substrate followsTalk to us →