Add Memory

Agent calls m.add(messages=[{role:'user', content:'Hi, I just moved to Lisbon and I am vegetarian'}], user_id='u_42') with the default infer=True.

With infer=True (default), Mem0 sends the messages to the extraction LLM and stores distilled facts (e.g., 'Lives in Lisbon', 'Is vegetarian') — not the raw chat turn. Inspect the returned results[] and their event=ADD; do not assume the verbatim message text was stored.

Operator needs to persist exact assistant tool outputs (a JSON config blob) without LLM distillation and calls m.add(messages, user_id='u_1', infer=False).

Set infer=False so Mem0 stores the message content verbatim with no fact extraction or dedup pass. Use this only when raw fidelity matters; expect no ADD/UPDATE/DELETE consolidation events and no LLM cost for extraction.

User previously stored 'Works at Acme'. In a new session the user says 'I just started at Globex', add()ed under the same user_id.

Mem0 should detect the contradiction and emit an UPDATE (or DELETE+ADD) so the employer fact reflects Globex, not both employers. The integrator must read the event and not leave the stale 'Works at Acme' memory active, which would corrupt future retrieval.