Store a memory. All memories start in Buffer and promote to Working/Core through access frequency and LLM quality gating. Procedural memories and lessons (tag=lesson) auto-promote to Working after 2h. Use supersedes to replace outdated memories by their ids.
Hybrid semantic + keyword search with budget-aware retrieval. Fast by default (~30ms cached, ~1s first query). Optional expand adds LLM query expansion (+1-2s) — only use for short/vague queries.
List recent memories by creation time. Good for session context recovery.
Full memory bootstrap for session recovery. Returns core (permanent knowledge), working (ongoing context/decisions), buffer (transient), recent activity, and session notes. Use workspace tags to filter by current work context. Compact mode (default) minimizes token usage.
Extract structured memories from raw text using LLM. Feed conversation logs or notes and get individual memories.
Quick keyword search. Lighter than recall — no scoring or budget logic.
Run a memory consolidation cycle. Promotes important memories upward, drops decayed entries. With merge=true, uses LLM to merge similar memories.
Get memory statistics: counts per layer, AI status, version.
Repair FTS search index. Removes orphaned entries and rebuilds missing ones. Safe to run anytime — idempotent.
Detailed health check: uptime, RSS memory, embed cache stats, AI config status.
Fetch trigger memories for a specific action. Call before performing an action (e.g. git-push, deploy) to recall relevant lessons and rules.
Delete a memory by ID. Use when a memory is outdated, incorrect, or redundant.
+4 more tools listed on main page