Now with llms.txt export

Turn any website into clean Markdown

Paste a URL. We crawl the whole site and hand you faithful Markdown files in the exact folder structure of the site — zipped, with llms.txt included. Perfect for RAG pipelines, docs migrations, and AI context.

Convert your site free See how it works

25 pages free · no credit card required

live demo — convert one real page, no signup

converts one real page in seconds · 5 free tries per hour

converted

That is one page. Get the whole site

How it works

Three steps, about a minute

No config files, no browser extensions, no scraping scripts. One input, sensible defaults.

Paste your URL

Drop in any public site or docs section. Cap the page count or scope the crawl to a path if you want — the defaults just work.

We crawl and convert every page

Pages stream in live and become faithful Markdown — tables, code blocks, images — mirrored in the site’s folder structure.

Download the ZIP

One archive with your whole site as .md files, plus auto-generated llms.txt and llms-full.txt, ready for any AI pipeline.

The full story, including URL → file mapping

Features

Fidelity-first, structure-obsessed

The output is meant to be used, not just downloaded — drop it straight into a repo, a vault, or a vector store.

Exact folder structure

/docs/getting-started becomes docs/getting-started.md. You download a usable docs tree, not a flat dump.

Faithful GFM conversion

Tables with inline formatting intact, fenced code blocks with language detection, and every link and image rewritten to an absolute URL.

llms.txt + llms-full.txt included

Every ZIP ships an auto-generated llms.txt index and an llms-full.txt with the complete content, following the llms.txt convention.

Live crawl progress

Watch pages stream into a growing file tree in real time. A blocked page never kills the crawl — failures are reported per page.

YAML front-matter on every file

Title, description, source URL, and fetch time on top of every file — ready for static site generators and RAG loaders.

Respects robots.txt

Disallow rules are honored by default, and the crawler paces itself politely instead of hammering the site.

Where it fits

RAG pipelines
LLM context
docs migrations
content audits
Obsidian vaults

Pricing

Start free, upgrade when you need volume

Free

Try it on your own site.

25 pages, on us
Every feature included
llms.txt + llms-full.txt in every ZIP

Start free

Pro

Whole sites, every month.

$9.99 /month

10,000 pages per month
Up to 500 pages per crawl
Cancel anytime, self-serve

Go Pro

See full pricing

FAQ

Questions, answered

Does it work on JavaScript-heavy sites?

We convert server-rendered HTML today, which covers the vast majority of docs sites, marketing sites, and blogs. JS rendering is on the roadmap. If a page comes back empty or blocked, it is reported per page — it never fails the whole crawl.

What is llms.txt?

A proposed standard: a Markdown file at /llms.txt that gives AI assistants a concise, curated index of your site. We generate one automatically from your live content — plus an llms-full.txt with everything — in every ZIP. Read the full explainer.

Do you respect robots.txt?

Yes, always. Disallow rules are honored by default, the crawler stays on the site you point it at, and it paces its requests politely.

Can I cancel anytime?

Yes — self-serve via Stripe from your settings page, no email required. You keep Pro access until the end of the billing period.

What happens when I hit the free limit?

The crawl stops gracefully and you keep every page already converted — nothing is thrown away. Upgrade to Pro to keep going with 10,000 pages a month.

Is my crawled content private?

Yes — it is stored only for you, visible only to your account, and deleted when you delete it. We never share it or use it to train models.

Your site, as Markdown, in about a minute

Paste a URL, watch the crawl, download the ZIP. Your first 25 pages are free.

Start free

25 pages free · no credit card required