- Get Started

Security by Design

OpenFlows' security is not a list of patches bolted onto the product — it falls out of the architecture. This page walks through the properties that make the system safe by construction, and the mechanisms that back each one.

The foundation: keep secrets out of the sandbox

The single most important decision is that worker workspaces hold no secrets and no credentials:

Remove the secrets from the sandbox and an entire class of "stolen key" attacks disappears.

Defense in depth

Beyond keeping secrets out, each risk has its own control:

PropertyHow it's enforced
Key exfiltrationNo keys in workspaces; models only reached through the central gateway
IdentityReal per-user login; every agent action inherits a real, attributable identity
Network isolationWorkspaces can reach only the control plane, GitHub, and the store — everything else denied
Command controlAgents must get approval before acting where it matters; only safe commands are permitted for verification
Review integrityBuilder and reviewer never share a filesystem; review happens at a distance
Gate integrityApprovals are single-use and only the reviewer can create them; an agent can’t approve its own work
AuditEvery step is a typed, recorded event, plus a full platform audit log
Multi-tenant isolationSeparate identity + separately namespaced coordination state

The review is trustworthy because it's isolated

The adversarial review only means something if SENTINEL can't be fooled or coerced by FORGE. Isolation buys this:

"When in doubt, don't approve"

The review posture is deliberately strict: if the required evidence is missing or unreadable, the reviewer must not approve — it holds the ticket or escalates rather than guessing. This one principle is worth more than any individual control, because it means the system would rather block than merge something unverified.

Trust is concentrated, not spread

Instead of sprinkling trust across many long-lived pieces, OpenFlows concentrates it in a single auditable place and keeps the rest ephemeral.

Auditability as a feature

For companies, "AI delivery" needs to stand up to review. Because every planning approval, review verdict, and merge is a typed, recorded event with an attributable identity, you can answer "what was the team doing, and why?" with a concrete trail — not a black box.

The result

Governed, auditable, and isolated by construction: this is what lets OpenFlows run AI agents autonomously inside your own infrastructure without lowering your security bar.