Qmd

Name: Qmd
Author: alsk1992

alsk1992/cloddsbot

12 installs
610 repo stars
Updated June 26, 2026
alsk1992/cloddsbot

qmd is a Claude skill (CLI-backed) that runs local hybrid search over indexed Markdown notes and docs on your machine.

About

qmd is a local search engine for Markdown notes, docs, and knowledge bases. Developers index a collection once, then run qmd search for fast BM25 keyword matches, or qmd vsearch and qmd query for semantic and hybrid results. It runs locally with GGUF models and a SQLite index on macOS or Linux. It is used to retrieve notes and related content from indexed Markdown files on disk.

Local hybrid search over Markdown notes and docs, indexed once
Fast BM25 keyword search by default, with optional semantic vsearch
Runs local GGUF models with SQLite-backed index, macOS and Linux

Qmd by the numbers

12 all-time installs (skills.sh)
Ranked #1,115 of 1,879 Documentation skills by installs in the Skillselion catalog
Data as of Aug 5, 2026 (Skillselion catalog sync)

At a glance

qmd capabilities & compatibility

Free and local; first run auto-downloads local GGUF models

Capabilities: notes search · semantic search · document retrieval
Use cases: research · web search
Platforms: macOS · Linux
Pricing: Free

From the docs

What qmd says it does

Local hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections.

SKILL.md

Prefer `qmd search` (BM25). It's typically instant and should be the default.

SKILL.md

npx skills add https://github.com/alsk1992/cloddsbot --skill qmd

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/alsk1992/cloddsbot/qmd.svg)](https://skillselion.com/skills/alsk1992/cloddsbot/qmd)

Installs	12
repo stars	★ 610
Last updated	June 26, 2026
Repository	alsk1992/cloddsbot ↗

What it does

Search local Markdown notes and docs and retrieve related documents from indexed collections.

Who is it for?

Searching and retrieving your local Markdown notes, docs, and knowledge bases.

Skip if: Code search across repositories, which the docs say to use dedicated code tools for.

When should I use this skill?

A user asks to search their notes, find related notes, or retrieve a Markdown doc from a collection.

What you get

searchable local index of a Markdown collection

By the numbers

3 search modes (search, vsearch, query)
few hundred tokens per chunk

Files

SKILL.mdMarkdownGitHub ↗

qmd - Quick Markdown Search

Local search engine for Markdown notes, docs, and knowledge bases. Index once, search fast.

When to use (trigger phrases)

"search my notes / docs / knowledge base"
"find related notes"
"retrieve a markdown document from my collection"
"search local markdown files"

Default behavior (important)

Prefer qmd search (BM25). It's typically instant and should be the default.
Use qmd vsearch only when keyword search fails and you need semantic similarity (can be very slow on a cold start).
Avoid qmd query unless the user explicitly wants the highest quality hybrid results and can tolerate long runtimes/timeouts.

Prerequisites

Bun >= 1.0.0
macOS: brew install sqlite (SQLite extensions)
Ensure PATH includes: $HOME/.bun/bin

Install Bun (macOS): brew install oven-sh/bun/bun

Install

bun install -g https://github.com/tobi/qmd

Setup

qmd collection add /path/to/notes --name notes --mask "**/*.md"
qmd context add qmd://notes "Description of this collection"  # optional
qmd embed  # one-time to enable vector + hybrid search

What it indexes

Intended for Markdown collections (commonly **/*.md).
In our testing, "messy" Markdown is fine: chunking is content-based (roughly a few hundred tokens per chunk), not strict heading/structure based.
Not a replacement for code search; use code search tools for repositories/source trees.

Search modes

qmd search (default): fast keyword match (BM25)
qmd vsearch (last resort): semantic similarity (vector). Often slow due to local LLM work before the vector lookup.
qmd query (generally skip): hybrid search + LLM reranking. Often slower than vsearch and may timeout.

Performance notes

qmd search is typically instant.
qmd vsearch can be ~1 minute on some machines because query expansion may load a local model (e.g., Qwen3-1.7B) into memory per run; the vector lookup itself is usually fast.
qmd query adds LLM reranking on top of vsearch, so it can be even slower and less reliable for interactive use.
If you need repeated semantic searches, consider keeping the process/model warm (e.g., a long-lived qmd/MCP server mode if available in your setup) rather than invoking a cold-start LLM each time.

Common commands

qmd search "query"             # default
qmd vsearch "query"
qmd query "query"
qmd search "query" -c notes     # Search specific collection
qmd search "query" -n 10        # More results
qmd search "query" --json       # JSON output
qmd search "query" --all --files --min-score 0.3

Useful options

-n <num>: number of results
-c, --collection <name>: restrict to a collection
--all --min-score <num>: return all matches above a threshold
--json / --files: agent-friendly output formats
--full: return full document content

Retrieve

qmd get "path/to/file.md"       # Full document
qmd get "#docid"                # By ID from search results
qmd multi-get "journals/2025-05*.md"
qmd multi-get "doc1.md, doc2.md, #abc123" --json

Maintenance

qmd status                      # Index health
qmd update                      # Re-index changed files
qmd embed                       # Update embeddings

Keeping the index fresh

Automate indexing so results stay current as you add/edit notes.

For keyword search (qmd search), qmd update is usually enough (fast).
If you rely on semantic/hybrid search (vsearch/query), you may also want qmd embed, but it can be slow.

Example schedules (cron):

# Hourly incremental updates (keeps BM25 fresh):
0 * * * * export PATH="$HOME/.bun/bin:$PATH" && qmd update

# Optional: nightly embedding refresh (can be slow):
0 5 * * * export PATH="$HOME/.bun/bin:$PATH" && qmd embed

If your Clawdbot/agent environment supports a built-in scheduler, you can run the same commands there instead of system cron.

Models and cache

Uses local GGUF models; first run auto-downloads them.
Default cache: ~/.cache/qmd/models/ (override with XDG_CACHE_HOME).

Relationship to Clawdbot memory search

qmd searches your local files (notes/docs) that you explicitly index into collections.
Clawdbot's memory_search searches agent memory (saved facts/context from prior interactions).
Use both: memory_search for "what did we decide/learn before?", qmd for "what's in my notes/docs on disk?".

/**
 * QMD CLI Skill - Quick Markdown Search
 *
 * Commands:
 * /qmd search <query> - BM25 keyword search (fast, default)
 * /qmd vsearch <query> - Vector semantic search (slower)
 * /qmd query <query> - Hybrid search (best quality, slowest)
 * /qmd index <path> - Index a directory
 * /qmd collections - List indexed collections
 */

import { execSync } from 'child_process';

function sanitizeShellArg(input: string): string {
  // Whitelist: only allow alphanumeric, spaces, hyphens, underscores, dots, slashes, and common punctuation
  return input.replace(/[^a-zA-Z0-9 \-_./,:!?@#%+=\[\]~]/g, '');
}

function checkQmd(): string | null {
  try {
    execSync('which qmd', { stdio: 'pipe' });
    return null;
  } catch {
    return `**qmd is not installed**

Install with:
\`\`\`bash
bun install -g https://github.com/tobi/qmd
\`\`\`

Or via cargo:
\`\`\`bash
cargo install qmd
\`\`\`

qmd provides fast BM25 keyword and vector semantic search over markdown files.`;
  }
}

async function execute(args: string): Promise<string> {
  const parts = args.trim().split(/\s+/);
  const cmd = parts[0]?.toLowerCase() || 'help';

  const installError = checkQmd();
  if (installError) return installError;

  try {
    switch (cmd) {
      case 'search':
      case 's': {
        const query = parts.slice(1).join(' ');
        if (!query) return 'Usage: /qmd search <query>';
        const result = execSync(`qmd search "${sanitizeShellArg(query)}"`, {
          encoding: 'utf-8',
          timeout: 10000,
        });
        return result || 'No results found.';
      }

      case 'vsearch':
      case 'vs': {
        const query = parts.slice(1).join(' ');
        if (!query) return 'Usage: /qmd vsearch <query>';
        const result = execSync(`qmd vsearch "${sanitizeShellArg(query)}"`, {
          encoding: 'utf-8',
          timeout: 30000,
        });
        return result || 'No results found.';
      }

      case 'query':
      case 'q': {
        const query = parts.slice(1).join(' ');
        if (!query) return 'Usage: /qmd query <query>';
        const result = execSync(`qmd query "${sanitizeShellArg(query)}"`, {
          encoding: 'utf-8',
          timeout: 60000,
        });
        return result || 'No results found.';
      }

      case 'index': {
        const path = parts[1];
        if (!path) return 'Usage: /qmd index <directory-path>';
        const result = execSync(`qmd index "${sanitizeShellArg(path)}"`, {
          encoding: 'utf-8',
          timeout: 120000,
        });
        return result || 'Indexing complete.';
      }

      case 'collections':
      case 'list': {
        const result = execSync('qmd collections', {
          encoding: 'utf-8',
          timeout: 5000,
        });
        return result || 'No collections indexed.';
      }

      default:
        return `**QMD - Quick Markdown Search**

  /qmd search <query>               - BM25 keyword search (fast)
  /qmd vsearch <query>              - Vector semantic search
  /qmd query <query>                - Hybrid search (best quality)
  /qmd index <path>                 - Index a directory
  /qmd collections                  - List indexed collections

Prefer 'search' for speed. Use 'vsearch' when keywords fail.`;
    }
  } catch (error) {
    return `Error: ${error instanceof Error ? error.message : String(error)}`;
  }
}

export default {
  name: 'qmd',
  description: 'Quick Markdown search - BM25 keyword and vector semantic search',
  commands: ['/qmd'],
  handle: execute,
};