skills.rest
BoraPerusic
BoraPerusicCOMMUNITY
Explore all skills by this author →
GitHub

conversation-memory

Memorize and retrieve conversational context across sessions with multi-tier memory.

Updated Apr 12, 2026
Search Tags:#context#llm#memory#persistence#conversation#entity-memory
One-click install
npx skills add https://github.com/BoraPerusic/agents --skill conversation-memory-boraperusic
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: conversation-memory
Source: https://github.com/BoraPerusic/agents/tree/main/skills/to%20try/conversation-memory
Command: npx skills add https://github.com/BoraPerusic/agents --skill conversation-memory-boraperusic

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Persistent memory systems address the challenge of losing context across interactions with LLMs, enabling continuity over short-term and long-term conversations and structured entity memories.

Core Features & Use Cases

  • Short-term memory for the current session
  • Long-term memory for cross-session persistence
  • Entity memory to remember facts about people, places, and things
  • Memory-persistence, memory-retrieval, and memory-consolidation to manage lifecycle
  • Use cases include maintaining context in ongoing conversations and recalling user preferences

Quick Start

Remember my last conversation context and key entities for future chats.

Frequently Asked Questions about conversation-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How does conversation memory work for maintaining LLM context?▼

Conversation memory persists context across sessions by implementing a multi-tier design with short-term, long-term, and entity memory to track continuity, user preferences, and facts over multiple interactions.

How do I persist conversation context and key entities for future chats?▼

You can persist context by applying memory-persistence and memory-consolidation techniques to store short-term session data and long-term entity memories for future retrieval across chats.

What is the best way to remember user preferences across multiple LLM sessions?▼

The best way to remember preferences is using entity memory and long-term cross-session persistence, which extracts and stores specific facts about users to enhance future personalization.

Can I retrieve specific facts about people and places from past conversations?▼

Yes, entity memory tracks and retrieves specific structured facts about people, places, and things, ensuring coherence when referencing those entities in ongoing multi-turn conversations.

How do I manage memory lifecycle and consolidation during multi-turn conversations?▼

You manage the memory lifecycle through memory-consolidation, which processes and organizes short-term session data into long-term persistence while applying privacy-aware retrieval constraints.

When should I use a multi-tier memory system instead of standard context handling?▼

Use multi-tier memory when multi-turn conversations require continuity and entity tracking, as standard context handling loses critical user preferences and structured facts across distinct sessions.

Related Skills

Explore More Software Engineering Skills→
samvanmesamvanme

memory-systems

Persist agent memory across sessions with layered memory and temporal knowledge graphs.

Community
Advanced
ArvincreatorArvincreator
637

Memory

Store and retrieve AI assistant memories in a vector database.

Community
Intermediate
ThedouglerThedougler

ai-engineer

Develop LLM applications, RAG systems, and agents with vector search and agent frameworks.

Community
Advanced
modu-aimodu-ai
1.2k

moai-foundation-context

Manage token budgets and persist session state for Claude Code workflows.

Official
Advanced