Retrieve relevant learnings for the current task context. Returns warnings (critical issues) and patterns (architectural guidance), scored and ranked by relevance.

Log a new learning entry. Validates, checks for duplicates/semantic duplicates, and appends to memory. Returns status (added/duplicate/semantic_duplicate/conflict/quarantined) and entry details.

Mark an existing learning entry as resolved by its timestamp.

Get memory system statistics: total entries, unresolved/resolved counts, severity/type/scope breakdowns, reinforcement patterns, and sleep cycle status.

Trigger a Sleep Cycle (consolidation): archives unresolved entries, generates promotion candidates, detects contradictions, and checks for stale entries.

Evaluate a structured prompt summary for learnable moments. Runs heuristic detectors on the summary, auto-logs high-confidence signals, and returns suggestions for medium-confidence ones.

Diagnostic report on AGENTS.md section health. Cross-references recent learnings with AGENTS.md sections, categorizing sections as active (referenced by learnings), cold (no references), and identifying unmatched learnings.

Capture a conversation interaction as memory. Extracts learnable moments from raw text and auto-logs them. Three-tier extraction: online LLM, offline LLM, heuristic fallback.