One sandbox per run, gone when it ends
Agent code and skills run in a sandbox made for one run. It has a hard deadline, its one credential expires with it, and teardown always runs.
An agent's loop and the code it writes run in their own short-lived sandbox. The user's token, model keys and tool secrets stay outside, every privileged act is brokered back through Cortx's controls, and outbound traffic is denied unless the run's grant names the host.
Each run splits in two. Model-controlled work runs in the sandbox; everything privileged stays with the Cortx control plane and is reached only through the broker.
Model-written code never runs where secrets live. The credentials, guardrails and ledger stay with the control plane, and every privileged act is brokered back, so escaping the sandbox gains nothing.
Four steps run for every sandboxed agent run. Select a step to jump to it.
Each turn, Cortx decides whether the run is off, observed or enforced, and which hosts it may reach, from your regulated profile, signed policy and workspace settings. It mints a short-lived run capability and, if hosts are allowed, a signed egress grant.
Each run gets its own short-lived pod under a sandbox runtime. Cortx Sentinel checks the guest kernel before the agent starts, and refuses anything weaker than the policy asks for rather than downgrading.
Shell and Python run inside. Every other tool and every model call goes back through the broker, where the plan gate, guardrails, approvals and audit run next to the secrets.
On finish, stop, error or deadline, the run is closed and its pod destroyed. Every credential it held expires just after its deadline, and a reaper ends anything missed.
A runtime name on its own is a request, not a control. Isolation comes from all three at once.
Every run records where it ran, the tier, the kernel, the image digest and the attestation, and shows it to the user.
Agent code and skills run in a sandbox made for one run. It has a hard deadline, its one credential expires with it, and teardown always runs.
The sandbox gets one run capability and a broker address. Never the user's token, a model key or a tool secret, so there is nothing inside worth taking.
A sandbox has no route out. Only hosts named in the run's signed grant are reachable, through one proxy, and every grant expires with the run.
How a sandbox fails safe, how tools are classified, and where it stands today.
If the sandbox or the requested tier isn't available, the run is refused. It never quietly falls back to running next to the secrets.
Only a short, explicit list of code-execution tools runs inside. Every other tool, including one added tomorrow, is brokered: a wrong guess costs a network hop, not a secret.
Each run records whether it was sandboxed, observed or refused, with its tier, kernel, image digest and attestation, and shows that to the user.
Agent Sandboxes ship off by default; you turn them on per workspace, in observe mode first. Recorded runs so far use a gVisor sandbox. The microVM tier is built to refuse to start until its kernel can be attested.
We'll run agent code in a sandbox, try to reach an ungranted host, and show where the run executed and what it could see.
We'd like to use Google Analytics to see which pages are read, how visitors find us, and roughly where in the world they are. Nothing is stored on your device unless you turn it on, and you can change your choice at any time. See our Cookie Policy for details.
What we collect