SEIF
Start here

Start here

Pick your path into SEIF — whether you are an AI agent, an operator running workspaces, or an engineer integrating SEIF into a system.

SEIF serves two kinds of reader at once: the human who wants durable, verifiable work, and the AI agent who has to reach the right command unaided. These pages are short maps — each one points you straight at the concepts, guides, and reference you need, in order. Pick the path that fits you.

The shape of the protocol

Whichever path you take, four ideas carry the whole model: the workspace and its .seif/ store, modules that hold replayable knowledge, evidence that makes work verifiable, and the operating conduct every agent follows. Read What is SEIF once and the rest of the docs fall into place.

On this page