Free tool

URL to Markdown

Paste a link. Get clean Markdown you can drop straight into an LLM prompt — and see exactly how many tokens you save by stripping the HTML. No signup, no key.

Fetches the page server-side and converts it.

This entire tool is six lines of backend

No scraping service, no conversion library glued together. The page you are on calls one endpoint, and the endpoint is this — a fetch, a conversion, two token counts, generated from a plain-English description and verified before it was saved:

.arguments
   url:string
validators.mandatory:x:@.arguments/*/url
validators.url:x:@.arguments/*/url
http.get:x:@.arguments/*/url
html2markdown:x:-/*/content
   url:x:@.arguments/*/url
openai.tokenize:x:@http.get/*/content
openai.tokenize:x:@html2markdown
yield
   markdown:x:@html2markdown
   html_tokens:x:@openai.tokenize/@openai.tokenize
   markdown_tokens:x:@openai.tokenize

That is the whole thing. Describe an endpoint in a sentence, and the Hyperlambda Generator writes and deploys it — then it is a tool your own AI agents can call over MCP. Want the page's metadata instead of its prose? URL to YAML does that. Run the platform yourself:

curl -fsSL https://hyperlambda.dev/docker-compose.yaml | docker compose -f - up

More free tools

Turning one page into clean Markdown is one of nine free tools here, each with the handful of backend lines that powers it printed on the page. See all of them — no signup on any of it.

Questions

Why convert a web page to Markdown for an LLM?

Raw HTML wastes tokens on tags, scripts and styling the model does not need. Markdown keeps the structure — headings, links, lists — at a fraction of the token count, which is cheaper to send and easier for a model to read. The counts on this page show the difference for any URL.

Does it run JavaScript on the page?

No. It fetches the server-rendered HTML and converts that. For pages that render entirely client-side you will get the shell rather than the content — the same trade-off every server-side fetch makes.

Can I run this at volume?

This is a free shared tool, so please keep it reasonable. If you need it at volume, run the endpoint yourself — it is the six lines above, MIT-licensed.

Can my AI agent call this directly?

Yes. On a Magic cloudlet every endpoint is also an MCP tool, filtered by role, so an agent can fetch-and-clean a URL the same way this page does.