Search long-term memories using hybrid retrieval (vector similarity + BM25 full-text + cross-encoder reranking). Returns semantically relevant memories ranked by quality.

Save important information to long-term vector memory. Auto-deduplicates and filters noise. Use for decisions, preferences, facts, project context — anything worth remembering across sessions.

Delete a memory by ID or search query.

Update an existing memory (text, importance, or category).

Memory usage statistics — total count, by scope, by category.

List recent memories, optionally filtered.

Smart extraction: use LLM to analyze conversation text and automatically extract important memories (preferences, decisions, facts, entities, events, patterns). This is the equivalent of autoCapture — call it at the end of important conversations.

Run the intelligent forgetting engine — removes low-quality, outdated memories based on Weibull decay model. Call periodically (e.g., once per session) to keep memory clean.

Log structured learning or error entries into .learnings/ directory for governance and later distillation. Use when: (1) a command/tool fails, (2) user corrects you, (3) you discover a knowledge gap, (4) you find a better approach.

Summarize governance backlog from .learnings/ files — pending, high-priority, and promoted counts.

Create a new skill scaffold from a learning entry and mark it as promoted.

Run the reflection pipeline — analyze conversation text, extract invariant rules and derived knowledge, store as reflection memories. This is the equivalent of the memory-lancedb-pro reflection system.

Bulk delete memories by scope, category, or age.

Migrate memories from legacy memory-lancedb format to current format.