Turn a website into structured LLM input.
Point the Actor at a domain. It discovers same-domain pages, extracts useful main content, and writes AI-readable outputs that can be reviewed before publishing.
llms.txtlinked page index- Optional
llms-full.txtwith page content - Per-page dataset exportable as JSON or CSV
- Batch and API use through Apify
Start with 10 pages and inspect every output.
Use a site you control, keep the first crawl small, and review the generated files before publishing them at a domain root.
example.com with the public website you want to process.llms.txt, llms-full.txt, and the page dataset in the run storage.Apify handles execution, usage billing, run history, and output storage. The public Actor listing is the source of truth for current pricing. This page does not sell a separate source-code licence; the implementation can be inspected in the linked public repository.
{
"websiteUrl": "https://example.com",
"maxPages": 10,
"includeFullText": true,
"maxContentCharsPerPage": 12000
}
Turn verified observations into a repeatable client audit.
The free method explains how to freeze scope, assign evidence IDs, separate pass, fail, not applicable, and unknown, publish weights before scoring, and compare later runs.
I am the independent solo developer behind this Actor and the separate audit kit. The kit is optional and does not include this Actor or promise rankings, citations, traffic, conversions, or revenue.
The generated files are drafts for review. No ranking, citation, traffic, or AI-discovery outcome is promised.