Conversation Memory
- 893 installs
- 29.9k repo stars
- Updated July 27, 2026
- davila7/claude-code-templates
conversation-memory is an agent skill that helps developers design persistent short-term, long-term, and entity-based memory systems for LLM assistants across multi-session conversations.
About
conversation-memory is a davila7 claude-code-templates skill sourced from vibeship-spawner-skills under Apache 2.0 that specializes in memory systems for AI assistants. The skill guides retrieval, relevance scoring, and context surfacing so agents remember users across months without flooding the prompt with every past message. It distinguishes short-term working memory, long-term durable storage, and entity-based memory for people, projects, and concepts. Developers reach for conversation-memory when building Claude or Cursor agents that need selective recall, intentional forgetting, and memory persistence beyond a single chat window.
- Implements tiered memory: short-term, long-term, and entity-based memory
- Handles memory persistence, retrieval, and consolidation automatically
- Memory-aware prompting that surfaces only relevant context
- Entity memory that stores and updates facts about users and objects
- Prevents anti-patterns of remembering everything or using a single undifferentiated store
Conversation Memory by the numbers
- 893 all-time installs (skills.sh)
- +33 installs in the week ending Jul 28, 2026 (Skillselion tracking)
- Ranked #1,178 of 16,659 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/davila7/claude-code-templates --skill conversation-memoryAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 893 |
|---|---|
| repo stars | ★ 29.9k |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 27, 2026 |
| Repository | davila7/claude-code-templates ↗ |
How do you add persistent memory to LLM agents?
Give their Claude or Cursor agents persistent short-term, long-term, and entity memory across conversations.
Who is it for?
Agent developers building assistants that must remember users, projects, and preferences across weeks of separate conversations.
Skip if: Developers needing simple single-session chat history or tasks unrelated to LLM memory system design.
When should I use this skill?
The user asks for conversation memory, long-term recall, entity memory, or persistent context across agent chat sessions.
What you get
Memory architecture with short-term buffers, long-term stores, entity graphs, and retrieval rules for multi-session agent context.
- memory architecture
- retrieval rules
- entity schemas
Files
Conversation Memory
You're a memory systems specialist who has built AI assistants that remember users across months of interactions. You've implemented systems that know when to remember, when to forget, and how to surface relevant memories.
You understand that memory is not just storage—it's about retrieval, relevance, and context. You've seen systems that remember everything (and overwhelm context) and systems that forget too much (frustrating users).
Your core principles: 1. Memory types differ—short-term, lo
Capabilities
- short-term-memory
- long-term-memory
- entity-memory
- memory-persistence
- memory-retrieval
- memory-consolidation
Patterns
Tiered Memory System
Different memory tiers for different purposes
Entity Memory
Store and update facts about entities
Memory-Aware Prompting
Include relevant memories in prompts
Anti-Patterns
❌ Remember Everything
❌ No Memory Retrieval
❌ Single Memory Store
⚠️ Sharp Edges
| Issue | Severity | Solution |
|---|---|---|
| Memory store grows unbounded, system slows | high | // Implement memory lifecycle management |
| Retrieved memories not relevant to current query | high | // Intelligent memory retrieval |
| Memories from one user accessible to another | critical | // Strict user isolation in memory |
Related Skills
Works well with: context-window-management, rag-implementation, prompt-caching, llm-npc-dialogue
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la462k185k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.379k15.8k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.378k92.5k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.375k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k8FAQ
What memory types does conversation-memory cover?
conversation-memory covers short-term working memory, long-term durable storage, and entity-based memory for tracking people, projects, and concepts. The skill emphasizes retrieval relevance so agents surface useful past context without overwhelming the prompt.
Which agents is conversation-memory designed for?
conversation-memory targets Claude Code and Cursor agents that need memory persistence across separate conversations. It applies Apache 2.0 patterns from vibeship-spawner-skills for selective recall and intentional forgetting.
Is Conversation Memory safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.