Feature · Library

Overview

What waits for you and what the crew learned.

Last changed

Generated from commit 39cc315 ·

How it works

What a memory has

  • a type: Working, Episodic, Semantic, Procedural or Social;
  • a scope: the organization, a team, one worker or one work item;
  • an authority: Explicit (stated in a document), Told (a person said it), Observed (measured from history) or Inferred (a model inferred it). Inferred memories always have lower confidence and never become policy;
  • a status: Active, Superseded, Archived or Expired;
  • a freshness, for example Fresh, Stale or Expires in some days.

Memory lists what the crew knows, with who taught it. Search it by words, and filter by kind, scope or who taught it. The Library overview searches memory, documents and conventions together and shows what waits for your decision.

Actions

  • Members: Tell the workforce a fact, and Verify a memory.
  • Admins: Archive (workers stop recalling it, but it is kept), Supersede, and Forget.

Forget removes the memory from what workers can find. Old audit entries and backups stay under their retention period.

From the help article Memory, checked against the product on .

What you can do

The operations this feature's screens call. Each one is POST /api/<name>, and the badge says who may call it.

  • listFacts

    Viewer

    Lists facts.

    Types: ListFactsRequest returns ListResponse<FactDto>

  • listMemories

    Viewer

    Lists memories.

    Types: ListMemoriesRequest returns PageResponse<MemoryDto>

  • searchKnowledge

    Viewer

    Searches knowledge.

    Types: SearchKnowledgeRequest returns ListResponse<KnowledgeHitDto>

  • listLessons

    Viewer

    Lists lessons.

    Types: ListLessonsRequest returns ListResponse<LessonDto>

  • listDocuments

    Viewer

    Lists documents.

    Types: ListDocumentsRequest returns PageResponse<DocumentSummaryDto>

  • listApprovedExamples

    Viewer

    Lists approved examples.

    Types: ListApprovedExamplesRequest returns ListResponse<ApprovedExampleDto>

  • listProcedures

    Viewer

    Lists procedures.

    Types: ListProceduresRequest returns ListResponse<ProcedureDto>

  • listMemoryInsights

    Viewer

    Lists memory insights.

    Types: ListMemoryInsightsRequest returns ListMemoryInsightsResponse

  • getPersona

    ViewerNo API tokens

    Gets persona.

    Types: EmptyRequest returns GetPersonaResponse

  • listSources

    Viewer

    Lists sources.

    Types: EmptyRequest returns ListResponse<KnowledgeSourceDto>

  • reviewLesson

    ApproverNo API tokens

    Reviews the lesson.

    Types: ReviewLessonRequest returns LessonDto

  • reviewFact

    ApproverNo API tokens

    Reviews the fact.

    Types: ReviewFactRequest returns FactDto

  • reviewPersonaTrait

    ViewerNo API tokens

    Reviews the persona trait.

    Types: ReviewPersonaTraitRequest returns PersonaTraitDto

  • verifyMemory

    Member

    Verifies memory.

    Types: MemoryIdRequest returns MemoryDto

  • createMemory

    MemberNo API tokens

    Creates memory.

    Types: CreateMemoryRequest returns CreateMemoryResponse

  • createDocument

    Member

    Creates a document.

    Types: CreateDocumentRequest returns CreateDocumentResponse

  • listWorkItems

    Viewer

    Lists work items.

    Types: ListWorkItemsRequest returns PageResponse<WorkItemSummary>

  • listMembers

    Viewer

    Lists members.

    Types: EmptyRequest returns ListMembersResponse

Screens

What it records

The feature writes these events to the audit log, the permanent record of what happened.

  • Persona extracted
  • Persona profile changed
  • Persona removed
  • Persona source added
  • Persona source removed
  • Persona trait reviewed

Generated from code at commit 39cc315 ·

Turn the numbers into shipped work.

Crewshal runs these choices for you: a persistent AI worker with memory and rules, on your Claude and Codex subscriptions.