Memoria Persistente para Agentes

Persistent memory system for AI agents inspired by Letta/MemGPT. Three-layer memory architecture (Core, Archival, Recall) that lets agents remember across sessions. Use when: (1) agent needs to recall user preferences, context, or decisions from past conversations, (2) starting a new session and needing context continuity, (3) user says 'remember this', 'you should know', or 'like last time', (4) agent detects important information worth persisting, (5) periodic memory maintenance during heartbeats. NOT for: simple Q&A with no persistence need.

by @renateparma·MIT-0