Semantic search over stored memories. Returns memories ranked by relevance to the query.

Store a new memory. Content is automatically scrubbed for secrets before embedding and storage.

Recall the most relevant memories for a project. Uses the project name as a semantic seed and returns the top-N most relevant memories scoped to that project.

Permanently delete a memory by its ID.

Export all stored memories as an array of memory records (JSONL-compatible). Optionally filter by project.

Import memories from a previously exported array of memory records. Duplicate IDs are overwritten.

List sessions grouped by project. Sessions are derived from memories that share a sessionId. Returns sessions sorted by most-recent activity.

Store a user preference as a memory with type=preference. Preferences are searchable and recallable like any other memory.

Record feedback on a recalled memory to improve future relevance. Rating: 1=helpful, 0=neutral, -1=not helpful.

Return collection stats: total memory count, memories per project, embedding model, and collection name.

Ping Qdrant Cloud and return connection status and latency.