Return the current project root, DB path, and export directory.

Switch project context (root + db + export path) and reconnect database.

Return server metadata and schema settings.

Create a new authoritative project entity.

Create an entity if missing or merge updates into an existing entity.

Update an existing entity's top-level state.

Add a piece of content to an entity.

Archive an entity without deleting its history or related project memory.

Delete an entity with guardrails; non-forced deletion requires prior archiving and no critical dependents.

Merge a duplicate source entity into a target entity with deterministic conflict handling.

Fetch an entity and optionally include related metadata, content, and events.

List entities with optional type, status, attribute, tag, and text filters.

Find likely duplicate or related entities before creating a new one.

Resolve a human-readable name to an existing entity when possible.

Reuse an exact entity when it already exists or create one with a generated stable id.

Create or update flexible metadata for an entity.

Set or merge tag labels for an entity.

Create a typed graph edge between two entities.

Create a relationship if missing, otherwise return the existing edge.

Delete a relationship by id and record the removal in project history.

List graph edges, optionally constrained to an entity and direction.

Write narrative content in one unified API with append|replace semantics.

Search narrative content using FTS5 when available.

Create a named snapshot of current project state.

Fetch a named snapshot and its captured entities.

List available view names for query_view discovery.

Query a named SQL view for generic reporting and model projections.

Report likely duplicates, low-quality records, and retention pressure in project memory.

Rebuild a task summary materialized table for faster open task queries.

Tune SQLite settings for throughput during heavy project-memory workloads.

Return decisions and recent supporting note excerpts without requiring ad hoc SQL.

Return a compact architecture-oriented node and relationship summary.

Return recent reasoning excerpts for quick AI context recovery.

Return dependency-oriented graph data with stable compact fields.

Return recent entities, content, and events to help an AI resume context quickly.

Prune older reasoning/log content while keeping the most recent records per entity and type.

Traverse outward relationship dependencies from an entity.

Initialize a project root entity and standard memory-area anchor entities.

Run a constrained read-only SQL query for diagnostics, analytics, and ad hoc retrieval.

Render markdown document views only after an explicit user request for a human-readable artifact.

Write generated markdown views only after an explicit user request for a human-readable artifact.