Initialize the local Universal Memory project layout.

Expose local cognitive persistence memory initialization and health check status.

Returns initialization state, fact counts, active rules, registered skills, approximate size, host validations, and recommended actions.

Load UMEM status, active project context, and the skills catalog once per session.

Report the active project layout without mutating files.

Copy curated legacy project content into visible shared project storage.

Run read-only environment diagnostics for Universal Memory.

Assemble the active cognitive memory context for AI agent operations.

Retrieves and compiles project-specific or global context facts, preferences, and rules formatted in Markdown, optimized for injection into system prompts.

Persist a memory fact through the shared safe mutation pipeline.

List memory facts with optional scope and status filters.

Purge one fact by id or all facts in a scope through the shared use case.

Requires confirm=True to execute.

List audit events for a scope.

List created snapshots for a scope.

Rollback the latest created snapshot for a scope.

Requires confirm=True to execute.

Configure an agent host manifest through the safe mutation pipeline.

Validate an agent host manifest without mutating files.

Synchronize approved active rules into supported instruction targets.

Review or decide a latent skill proposal.

If decision is omitted, returns the suggested name, scope, purpose, evidence, and explicit choices for a follow-up call.

Explicitly track or increment recurrence for a latent skill opportunity.

Generate the physical Agent Skill structure for an approved latent skill.

Create a canonical Agent Skill without native sync unless sync is explicit.

Create an editable draft skill without canonical publish or native runtime writes.

Validate a draft, canonical skill, or local skill path without mutating files.

Publish a validated draft as canonical and optionally sync native targets.

Explicitly copy a project skill into shared repository content.

Promote an approved latent skill candidate into a canonical Agent Skill.

Synchronize canonical Agent Skills into native targets with optional git warnings.

Import an existing native or local Agent Skill directory into canonical UMEM storage.

Adopt an existing skill directory into UMEM without creating duplicate slugs.

Update canonical skill content with validation and optional native sync.

Rename a canonical skill slug while blocking unmanaged destination conflicts.

Plan or apply managed-only native target cleanup for a canonical skill.

Plan or apply managed-only repair for orphan native skill targets.

List registered skills and candidates without mutating local state.

Review read-only latent skill recommendations captured by explicit skills.track evidence.

This never promotes, imports, syncs, creates, or mutates skills. dry_run is accepted for API clarity; non-read-only behavior is not supported.

Inspect metadata and triggers for one registered skill.

Reactivate an ignored latent skill through the shared safe mutation pipeline.

Deactivate an active latent skill without deleting its physical SKILL.md.

Update skill metadata or markdown through the shared safe mutation pipeline.