QMD Memory Search

by sbusso

QMD Memory Search is an AI Engineering skill for Claude Code, published by sbusso in claudeclaw.

193 stars60 forkson sbusso/claudeclawAdded 2026/09/06Repository updated 2026/08/12

View source on GitHub Download repo ZIP

agentagentic-aiclaude-codeopenclaw

Install in seconds

Install QMD Memory Search

Copy QMD Memory Search into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/sbusso/claudeclaw/tree/main/skills/add-qmd ~/.claude/skills/add-qmd

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/sbusso/claudeclaw.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/add-qmd/SKILL.md in sbusso/claudeclaw
Installs to: ~/.claude/skills/add-qmd
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 3278 skills

What QMD Memory Search does

QMD Memory Search upgrades ClaudeClaw’s grep-based memory search with local hybrid BM25, vector semantic search, and LLM reranking. Use it when you want better recall across large memory collections without API keys.

QMD Memory Search is cataloged under AI Engineering on DirSkills. QMD Memory Search comes from a repository tagged agent, agentic-ai, claude-code and openclaw.

Documentation

README

Excerpt

Add QMD Memory Backend

QMD (https://github.com/tobi/qmd) is a local search engine for markdown files. It combines BM25 keyword search, vector semantic search, and LLM re-ranking — all running on-device via node-llama-cpp with GGUF models.

This skill upgrades ClaudeClaw's built-in grep-based memory_search MCP tool with QMD's hybrid search, giving agents much better recall across large memory collections.

Prerequisites

ClaudeClaw with memory tools already working (memory_search, memory_save, memory_get)
~2GB disk space for GGUF embedding + reranking models (downloaded on first run)
Node.js 20+

This is the opening of the README. Read the full README on GitHub.

Frequently asked about QMD Memory Search

What else does sbusso publish alongside QMD Memory Search?
QMD Memory Search is one of 25 skills that DirSkills catalogs from sbusso/claudeclaw, the repository it ships in. Its siblings there include Add Compact Command, Add Gmail and Add Reactions. Each one is a separate skill with its own page in this directory, installs the same way QMD Memory Search does, and is maintained by sbusso in that same repository. The rest of the collection is listed on the sbusso/claudeclaw page.
How does QMD Memory Search compare to other AI Engineering skills?
QMD Memory Search ranks #2885 by stars among the 3278 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of QMD Memory Search against them. Open each page to compare what they document and how they install.