skills.rest
wyhlovecpp
wyhlovecppCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

memory-system

Index Markdown files into vector and full-text search with SQLite.

Updated Feb 22, 2026
Search Tags:#indexing#search#memory#sqlite#semantic-search#knowledge-base#vector-search
One-click install
npx skills add https://github.com/wyhlovecpp/my-codex-settings --skill memory-system-wyhlovecpp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory-system
Source: https://github.com/wyhlovecpp/my-codex-settings/tree/main/skills/by-category/knowledge-management/memory/memory-system
Command: npx skills add https://github.com/wyhlovecpp/my-codex-settings --skill memory-system-wyhlovecpp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires sentence-transformers, numpy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables the organization and retrieval of knowledge across multiple sessions by indexing Markdown files into a semantic search system.

Core Features & Use Cases

  • Indexing and Search: Converts Markdown files into vector and full-text searchable data, facilitating quick retrieval of relevant information.
  • Memory Management: Supports adding, cleaning, and maintaining a knowledge base for ongoing reference.
  • Use Case: A user maintains extensive notes in Markdown; using this Skill, they can quickly find relevant information across their personal knowledge repository using natural language queries.

Quick Start

Use the memory-system skill to create an index of your Markdown notes and perform a semantic search to find related content.

Frequently Asked Questions about memory-system

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

FAQPage Schema
How do I perform semantic search across my Markdown knowledge base?▼

This Skill indexes Markdown knowledge base files into a local SQLite database, generating vectors with sentence-transformers to retrieve relevant information using natural language queries.

Can I use SQLite and sentence-transformers to build a personal knowledge base?▼

Yes, SQLite and sentence-transformers build a personal knowledge base from Markdown files, enabling both full-text and vector search to efficiently manage and retrieve your notes.

What is cross-session memory management for Markdown notes?▼

Cross-session memory management for Markdown notes indexes files into a persistent semantic search system, allowing you to retrieve knowledge across different sessions without re-reading entire documents.

Do I need numpy to index Markdown files for vector search?▼

Yes, numpy alongside sentence-transformers indexes Markdown files for vector search, handling the numerical operations and embedding generation required for semantic retrieval.

How do I maintain and clean a semantic search index?▼

To maintain and clean a semantic search index, this Skill supports adding, cleaning, and maintaining knowledge base entries within the SQLite database to ensure Markdown notes remain accurate and retrievable.

What is the best way to retrieve research documents using natural language queries?▼

The best way to retrieve research documents using natural language queries is indexing Markdown files into a vector search engine, matching semantic meaning rather than exact keywords to find relevant content.

Related Skills

bahayonghangbahayonghang
16

memory-system

Index Markdown notes into a local SQLite vector/full-text index.

Community
Intermediate
shsteimershsteimer

Searching AEM Documentation

Search AEM Live documentation and return ranked results with relevance scores.

Community
Basic
anderskevanderskev
20

sqlite-vec

Store and query vector embeddings in SQLite using vec0 virtual tables.

Community
Intermediate
MadAppGangMadAppGang
278

semantic-code-search

Index codebases and search by semantic meaning with hybrid retrieval.

Official
Intermediate