On-device · Readability + Turndown

Clean pages, clean Markdown.

Turn any web page into clean, readable Markdown. Readability + Turndown, 100% on-device.

Instant
100% private
GFM tables
Why Cleaner

Distill the web. Locally.

No servers, no API calls. Just your browser and the page.

100% private

Page content is processed entirely in your browser. Nothing is uploaded.

Readability first

Mozilla's Readability extracts the main content, stripping ads and clutter.

Turndown Markdown

Clean, semantic Markdown output via Turndown. Ready for Obsidian, Notion, or anywhere.

Copy or download

One click to copy to clipboard or download as a .md file.

How it works

Three steps. Zero servers.

  1. 01

    Paste a URL

    Enter the page URL you want to clean. The page is fetched and parsed locally.

  2. 02

    AI extracts content

    Readability identifies the main article, stripping navigation, ads, and sidebars.

  3. 03

    Copy your Markdown

    Get clean Markdown output. Copy to clipboard or download as a file.

Complete guide

About the web-to-Markdown cleaner

A free tool that turns messy web pages, pasted HTML, and article links into clean Markdown — stripping ads, newsletters’ chrome, tracking pixels, and navigation clutter in the process. It is built for researchers saving sources, writers collecting reference material, and anyone feeding documents into an LLM or note system that works best with plain text.

How it works

The pipeline runs entirely client-side. Mozilla’s Readability algorithm (the same engine behind Firefox Reader View) identifies the main article content, then Turndown converts the clean HTML into Markdown with options for GFM tables, preserved links, H1 titles, and image handling. You can paste raw HTML directly, drop in page source, or fetch a URL — fetched pages are requested from your own browser session, and sites that block cross-origin requests can simply be pasted instead.

Limits & requirements

Some sites disallow cross-origin fetching from the browser; pasting the page’s HTML always works as a fallback. Paywalled content requires a page you can already access in your session. Output quality depends on how the source page is structured — well-formed articles clean up best.

Privacy

No document text passes through our servers — conversion runs in your tab, and no content from your pages is logged, stored, or used for training.

Support

Questions, answered.

Not directly — browsers block cross-origin fetches without a proxy. Open the article, copy the page source (or select-all and copy), then paste here. Everything stays on your device.