Conversation Memory

This implements a tiered memory system for LLM conversations with short-term session storage, long-term persistence, and entity tracking. The pattern here is solid: buffer the current conversation, extract and score memorable content, consolidate important interactions into long-term storage, and maintain a separate entity store for facts about people, places, and things. You'd use this when building chatbots or assistants that need to remember context across sessions without stuffing everything into the prompt. The main gotcha is memory growth, the source includes lifecycle management code with importance scoring and automatic pruning, which you'll definitely need. Works with Mem0, LangChain Memory, or Redis depending on your stack.

skills.sh installs: 1.3K
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill conversation-memory --agent claude-code

Installs into .claude/skills of the current project.

Files

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

Does_not_cover: Knowledge graph construction, Semantic search implementation, Database administration
Boundaries: Focus is memory patterns for LLMs, Covers storage and retrieval strategies