agent-memory-design

Designs cross-session memory for AI agents: layered working, session and durable stores, canonical entity identity, vector and graph retrieval with temporal validity, consolidation and bounded context loading. Use when the user asks to "give the agent long-term memory", "remember preferences across sessions", "track facts with valid-from and valid-until dates", "compare memory frameworks like Mem0 or Zep", or "build a memory prototype". Not for model fine-tuning, vector-database administration, or ranking memory products by benchmark claims.

Version

v1.0.0

Size

27 KB

Updated

2026-10-02

Your client verifies the signature before reading. This explicit manual read is available on every plan. Free automatically loads five chosen skills; paid plans automatically load relevant skills across the library.