Architecture

This section explains how the OpenFlows system is put together — in plain language, with no code. It's written for anyone who wants to understand the system well enough to operate it, extend it, or evaluate its security.

At the highest level, OpenFlows divides the world into two halves: a control plane where the system's brain lives, and a work plane where disposable agents do the actual coding. Everything else in the architecture serves that split. Two systems cooperate: Coder governs where agents run; OpenFlows governs how they coordinate.

The centre of the picture

One long-lived component — the Controller (the brain) — runs inside a single, trusted NEXUS workspace in the control plane. It is the only piece that talks to Coder's API to create workspaces and coordinate agents. Around it sit a shared coordination store that holds the team's state, and the many short-lived worker workspaces where FORGE, SENTINEL, VESSEL, and LORE do their individual jobs — each one provisioned for a single task and torn down when it's done.

The architecture is built on a simple thesis: architecture is the product. OpenFlows encodes the engineering — the review gates, the recovery patterns, the trusted boundaries — so that agents produce software, not just code. The guardrails that run through the whole design are straightforward: plan before code, when in doubt, don't approve, bounded recovery then human escalation, and no secrets in worker workspaces.