automation

Gharmonize

Name: Gharmonize
Author: G-grbz

All-in-one media downloader and converter with Web UI, desktop builds, and advanced ffmpeg automation. Built on yt-dlp · Supports YouTube, Spotify, Apple Music

129 stars4 forksJavaScriptUpdated 8/17/2026100% free · open source

What it does

Gharmonize is an all-in-one media downloader and converter that supports multiple platforms, including YouTube, Spotify, Apple Music, and Deezer, with advanced ffmpeg automation and a user-friendly Web UI.

When to use it

•When you need to download and convert media files from various online platforms in bulk
•When you want to automate media file processing and conversion for your startup's content creation needs
•When you require a self-hosted solution for media file management to ensure data privacy and security

Ready-to-paste prompt

yt-dlp -f bestaudio --output '%(title)s.%(ext)s' https://www.youtube.com/watch?v=dQw4w9WgXcQ

Heads up: Ensure you have the necessary dependencies installed, including ffmpeg, and that you have the correct version of Node.js (at least 14.17.0) to run Gharmonize smoothly

Saves to your device

Use with Claude

New

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

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/gharmonize && curl -fsSL https://workflowstacks.com/api/skills/gharmonize/claude-skill -o ~/.claude/skills/gharmonize/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 Gharmonize works

Codeflow

Free to inspect

Gharmonize is a very large JavaScript project (~64k lines across 87 code files, plus 16 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, GPL-3.0 license, has a test suite.

Size

Very large codebase

~64k lines · 87 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Node.js · Docker

No API keys detected

JavaScript 98%HTML 2%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
app.js
Where the program starts running
3
package.json
Dependencies and the commands it exposes

What's in each folder

modules/Sub-packages / plugins45 files

docs/Documentation11 files

routes/Folder9 files

scripts/Helper scripts4 files

electron/Folder2 files

public/Images & static assets36 files

test/Tests — proof it works16 files

.github/CI / automation (GitHub Actions)8 files

READMEHas testsDocumentedCI checksDocker readyGPL-3.0 licenseUpdated this month

Use with Claude

New

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

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/gharmonize && curl -fsSL https://workflowstacks.com/api/skills/gharmonize/claude-skill -o ~/.claude/skills/gharmonize/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.

Quick Actions

Details

Creator

G-grbz

Language

JavaScript