VYCEAccess

The trust layer for agents you didn’t write

Run agents you
can’t trust. On
infrastructure you can.

A sealed runtime and open protocol that lets a platform run anyone’s agent next to real data — and certify, per run, that it never leaked, acted, or wandered. Containment you can attest. Trust an ecosystem can build on.

bubblewrap · seccomp · cgroup v2 · per-tenant egress · append-only audit

run r_8f2c9a4e contained
signatureverified
sandboxsealed
egressmodel only
modelyou choose·
actiongated
replyscrubbed
sandboxdestroyed
auditwritten
prompt never persisted · keys dropped on teardowncertified ✓

Not a way to build agents. The way to certify them.

Every invocation, contained

A box that opens, does one job, and burns.

The agent is untrusted, so it runs inside a boundary the kernel enforces — bubblewrap, seccomp, cgroups — not a policy doc you hope holds.

01stage

Signed

Every request is signed. No valid signature, no entry — one inbound door, nothing else.

02stage

Sealed

A fresh sandbox per run: no disk, no peers, no network except one guarded exit. The agent starts with nothing.

03stage

Routed

It can reach exactly one thing — the model you approved. Internal services, metadata, other tenants: denied at the wire.

04stage

Gated

If it must act, it proposes — a policy gate you control decides and executes. The agent never holds the keys.

05stage

Scrubbed

Secret-shaped values are stripped from every reply before it leaves the box. Nothing smuggles out.

06stage

Sealed shut

The box is destroyed. Keys and prompts in memory vanish with it — and a signed receipt lands. Never the content.

Two tiers of trust

Certify what an agent can't do. Not whether it's any good.

Containment is a claim about boundaries, not judgment — that's exactly why an auditor and an insurer can take it to the bank. Quality is a layer we measure separately.

Tier 0 — Observation

Certified it cannot act.

The agent observes and reports. Actuation isn’t a permission you can grant — it isn’t on the path. The purest, most-underwritable guarantee there is: an absolute claim about what could not have happened.

attestable · absolute · zero blast radius
Tier 1 — Mediated action

The agent proposes. A gate disposes.

When agents must act, they don’t. They emit an intent; a policy gate you control decides, executes, logs, and can reverse it. Certified: every action passed a gate the agent couldn’t bypass — and it never held the credential.

Agentuntrusted
proposes
Gateyou control
executes
Actionlogged · reversible
direct actuation denied — the agent never holds the credential, never makes the call, can’t bypass the gate.

The agent proposes — it never disposes. That one rule is the whole product: ride the action wave without ever being the thing that pulls the trigger.

Why it holds

Built to be trusted with the part that matters.

Open

A protocol, not a vendor.

The spec and reference runtime are open. The drill suite IS the definition of “contained.” Implement it yourself or run ours — certification travels across the ecosystem, not one vendor's walls.

Provable

What auditors cite.

Isolation you can prove, not promise. Every boundary — cross-tenant, egress, actuation, exfiltration — is enforced by a drill that fails the build the moment it regresses.

Insurable

What insurers price.

Lowest-level control of the sandbox, down to the seccomp filter. You can't underwrite what you don't own — so we own the whole stack, and the certification is built to be priced.

Data sovereignty

Keep the data
in your walls.

Point an agent at a model you host — Ollama, vLLM, your own endpoint — and the prompt never leaves your infrastructure. No third party ever sees it. Same containment, zero external exposure. The story a regulated bank or hospital can sign.

How isolation is enforced →
Anthropic / OpenAIthat provider sees it
Your Ollama / vLLMnobody but you
Your own gatewaynobody but you

Running agents you didn’t write?

Vyce is in private access while we onboard the first hosts. Tell us what you’re running — we’ll get you contained.