Core concepts
Knowledge Model
Every entry is typed and scoped, so agents can retrieve exactly the context that applies to the task in front of them.
Entry types
| Type | Use for |
|---|---|
rule | Hard constraints the codebase should enforce |
architecture | System structure and rationale |
pattern | Reusable implementation approaches |
decision | Decision records and tradeoffs |
convention | Naming, formatting, and style agreements |
note | Observations, caveats, and open questions |
Scopes
| Scope | Use for |
|---|---|
global | Applies everywhere |
team | Applies across multiple repos |
repo | Specific to one repository |
domain | Specific to a bounded area in one repo |
Metadata and body
Entries also support tags, optional URLs, arbitrary metadata, and confidence scores (0–1). Two content fields serve different consumers:
content— the plain searchable text.body— a structured, renderable version made of blocks: headings, paragraphs, lists, quotes, code, callouts, and link lists. Reader UIs likeknowit previewrender this.
When body is omitted, Knowit derives paragraph blocks from content automatically.
Storage format
Default project storage is .knowit/knowledge.jsonl — one JSON entry per line, readable, reviewable, and friendly to git diffs. Global and custom scopes can use SQLite when you want a private local database or a shared database path. See Team Memory.