memory

Store and retrieve user context via embedding-based semantic similarity search.

330|47|Updated Aug 30, 2020

Search Tags:#context retrieval #embeddings #similarity search #MCP tools #semantic memory #knowledge persistence

Ready to run

npx skills add https://github.com/harperreed/dotfiles --skill memory-harperreed

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory
Source: https://github.com/harperreed/dotfiles/tree/main/.claude/skills-archive/memory
Command: npx skills add https://github.com/harperreed/dotfiles --skill memory-harperreed

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Memory helps you store useful information so it can be recalled later without rereading past conversations or notes.

Core Features & Use Cases

Store long-term context: Save important preferences, decisions, and project-specific details for future sessions.
Semantic similarity search: Retrieve related memories by meaning rather than exact keywords.
Context recall for topics: Fetch the most relevant stored information to ground new responses.
Memory management: List recent memories and delete items when they are no longer accurate.

Quick Start

Use the memory skill to save a preference by asking: memory add "User prefers TypeScript over JavaScript for new projects" with tags preferences and programming.

Frequently Asked Questions about memory

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

FAQPage Schema

How do I persist user preferences and decisions for cross-session context recall?▼

To persist user context for cross-session recall, you store preferences and decisions using semantic memory tools that save information as embeddings. This allows future sessions to retrieve relevant knowledge by meaning without rereading past conversations.

How does semantic similarity search retrieve stored memory by meaning instead of exact keywords?▼

Semantic similarity search retrieves stored memory by converting queries into embeddings and comparing them against saved context vectors. This matches items by underlying meaning rather than requiring exact keyword overlap, returning the most relevant snippets.

What's the best way to log and extract project-specific context for long-term knowledge persistence?▼

The best way to log project-specific context is using the memory skill's extraction workflows to save important details as embeddings. This ensures long-term knowledge persistence by capturing project-specific information for future semantic retrieval.

Do I need MCP tools to use semantic memory for storing and retrieving context?▼

Yes, you need MCP memory tools to use this semantic memory skill. The skill requires MCP tools specifically for storing vectors, searching by query meaning, listing recent entries, deleting items, and returning relevant context snippets.

Can I list recent memory entries and delete stored items when they are no longer accurate?▼

Yes, you can list recent memory entries and delete stored items when they are no longer accurate. The memory management workflow includes list and delete operations to help maintain relevant context and remove outdated information.

When should I not use embedding-based semantic memory for context retrieval?▼

You should not use embedding-based semantic memory when exact keyword matching is required, or when the overhead of managing vector storage outweighs the benefit of semantic recall for short, highly transient conversations that do not require long-term persistence.