conversation-memory

Installation
Summary

Persistent memory systems for LLM conversations with tiered storage and intelligent retrieval.

  • Implements three memory types: short-term (immediate context), long-term (historical facts), and entity-based (facts about specific entities)
  • Provides memory retrieval and consolidation capabilities to surface relevant memories without overwhelming context windows
  • Addresses critical concerns including unbounded memory growth, retrieval relevance, and strict user isolation to prevent cross-user data leaks
  • Works alongside context management, RAG, and prompt caching skills for cohesive conversation state handling
SKILL.md

Conversation Memory

Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory

Capabilities

  • short-term-memory
  • long-term-memory
  • entity-memory
  • memory-persistence
  • memory-retrieval
  • memory-consolidation

Prerequisites

  • Knowledge: LLM conversation patterns, Database basics, Key-value stores
  • Skills_recommended: context-window-management, rag-implementation

Scope

Related skills
Installs
1.0K
GitHub Stars
37.3K
First Seen
Jan 19, 2026