Search past memories by content. Call this when the user references past work ('do you remember', 'last time', 'previously') or when you need context from a previous session. Pass the user's prompt as query. Returns ranked results from FTS5. If empty, no memory is needed for this turn. For browsing by tags or time window, use memory_recall.

Store a memory. You MUST call this after every non-trivial turn. Choose the type based on what you are saving:

• episodic: an event that happened — 'fixed the login bug in auth.py', 'user asked for a tic-tac-toe game', 'refactored auth module to use JWT'. Concrete actions and outcomes.

• semantic: a durable fact that stays true — 'user prefers Python 3.12', 'project uses pytest', 'auth uses JWT', 'user communicates in Polish'. Knowledge about the user or project.

• procedural: a how-to with steps — 'run tests with pytest -x', 'deploy via npm run build && rsync', 'start dev server: python -m backend.main'. Steps to accomplish something.

Set confidence below 1.0 for inferences, assumptions, or guesses. Use tags for filtering (e.g. project name, topic). Episodic payload keys: session_id, agent, task, outcome, parent_id, metadata. Store one memory per distinct thing. ALWAYS skip idle chat, greetings, and trivial responses. Forgetting to store = permanent loss of the session.

Browse memories of one type, newest first. Filter by tags and time window. Use for 'what did I do recently' or 'what happened in this session'. Not for per-turn recall — use memory_search for that.