workflowstacks
analytics

qmd

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
30,536 stars+134★ this week1,921 forksTypeScriptInstall verified Sep 21Updated 10/15/2026100% free · open source
What it does

QMD is a locally-run command-line search engine for your documents, allowing you to index and query your knowledge bases, meeting notes, and other text files.

When to use it
  • •When you have a large collection of unorganized notes and documents and need to find specific information quickly
  • •When you want to keep your data local and avoid relying on cloud-based search services
  • •When you need to search across multiple file formats, such as Markdown, PDF, and plain text
Ready-to-paste prompt
qmd search 'meeting notes from last week' to find relevant documents containing that phrase
Heads up: QMD requires Node.js 14 or later to run, so ensure you have a compatible version installed before attempting to install or use the tool
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box✓ Install verified 9/21/2026

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/qmd && curl -fsSL https://workflowstacks.com/api/skills/qmd/claude-skill -o ~/.claude/skills/qmd/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How qmd works
Codeflow
Free to inspect

Qmd is a large TypeScript project (~27k lines across 94 code files, plus 49 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license, has a test suite.

Size
Large codebase
~27k lines · 94 code files · ~4 h to skim
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 2 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Node.js
TypeScript 86%Python 11%Shell 1%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    CLAUDE.md
    The instructions the AI actually follows
  3. 3
    bin/qmd
    Where the program starts running
  4. 4
    src/index.ts
    Inside src/ — the main logic begins here
What's in each folder
src/Core code — the actual logic23 files
skills/Prompts, skills & agent definitions5 files
bin/Command-line entry points1 files
docs/Documentation1 files
finetune/Folder62 files
tools/Helper scripts36 files
scripts/Helper scripts9 files
.claude-plugin/Plugin manifest — what gets installed1 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
tobi
Language
TypeScript
Category
analytics
Published
12/8/2025

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/qmd.svg)](https://workflowstacks.com/skills/qmd?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Free n8n template

Meeting Summary Email

Paste any meeting transcript into a private form and get a clean summary email — decisions, action items with owners, open questions.

Outcome guide

Automate your meeting summaries

A private form takes any transcript (from Zoom, Meet, Otter, Fireflies) and emails you back a structured summary: a TL;DR, the decisions made, and action items with owners.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

Ready-to-run pack · one-time $29

Competitor Watch

Get emailed the moment a rival changes their price or pitch.

Includes the tested workflow and a written setup playbook. Needs: No extra API — just watches the pages you list.

See what you get

Related skills

More analytics tools founders pair with this one.

analytics★ 113,787
d3
Bring data to life with SVG, Canvas and HTML. :bar_chart::chart_with_upwards_trend::tada:
analytics★ 111,554
Boost code reliability with TypeScript for faster product launches
Founders building JavaScript products gain static typing, early bug detection, and maintainable code—backed by 111k+ GitHub stars.
analytics★ 103,038
Fast Design with Open-Design
Get native app design with web, desktop, mobile prototypes. For founders needing local-first design tools.
analytics★ 39,509
Umami: Privacy‑First Web Analytics with 39k+ GitHub Stars
Get clear, GDPR‑compliant insights into user behavior without third‑party trackers. Ideal for founders who need product analytics without sacrificing privacy.
analytics★ 94
extension-gen-ai: Accelerate Looker Insights with AI‑Powered Exploration
Leverage LLM‑driven queries to simplify data exploration and surface dashboard insights fast—ideal for founders who need rapid analytics without manual digging.
analytics★ 23
app-lookml-diagram: Visualize LookML
See your LookML models clearly with app-lookml-diagram, a tool for startup founders using Looker.