Knowledge & Search
Store, index and retrieve information with permissions and provenance intact.
Primitive already persists files, indexes text and performs permission-filtered search. The wider Knowledge layer aims to connect those materials to objects, evidence, memory and domain context.
Primitive can search your stuff, but the bigger goal is to know what each piece of information belongs to, who is allowed to see it and why it matters.
Search answers 'where is something?'; Knowledge answers 'what is this, how does it relate, and what can rely on it?'. Primitive has the retrieval foundations today, while the richer knowledge graph and semantic relationships remain an expanding capability.
Implemented retrieval
File persistence, text indexing and permission-filtered search are part of the canonical Workspace capability set.
Knowledge boundary
A retrieved item is not automatically truth. Source identity, provenance, permissions and evidence strength remain separate dimensions.
Reuse before rebuild
The canonical START_HERE flow requires workers to inspect estate and OS reuse indexes before creating parallel knowledge, memory, retrieval or context machinery.
Where this description comes from
These pointers are the authority behind the status and technical description. If implementation and documentation disagree, the canonical implementation or Control contract wins and this page should be corrected.