Tools
Generate the three files that tell AI systems how to read your site
Point the generator at a domain. It builds the content index, the crawler rules and the opt-out tags, ready to copy.
Generate yours free See the packageFree with an account. No card, no credits spent.
What it generates
One run produces the full set. Copy any panel to the clipboard, download a single file, or take the lot as a bundle.
llms.txt
A markdown index of your site's pages with titles and descriptions, in the format set out by the llmstxt.org spec - plus an llms-full.txt variant carrying the page text itself.
robots.txt directives
Rules for 14 named AI crawlers. Allow everything, block everything, or set each bot's access individually with its own path.
Meta tags
The noai and noimageai head snippets, for opting individual pages out of AI training datasets rather than the whole domain.
How it works
Enter a domain
Just the hostname. Nothing has to be installed, and the site does not need to be yours to inspect what a generated file would look like.
We find your pages
The generator reads your sitemap.xml (following a sitemap index, or whatever path your robots.txt points at) and takes up to 40 URLs from it.
We read each page's own words
Every discovered page is fetched for its <title> and meta description. No model writes the descriptions - the file says what your pages already say about themselves.
Review, then publish
Edit anything you want to change, then upload llms.txt to the root of your domain and paste the robots rules and meta tags where they belong.
What llms.txt actually is, and what it is not
llms.txt is a plain markdown file at the root of a domain that lists your important pages with a line of description each. The idea, proposed at llmstxt.org, is the same one behind robots.txt and sitemap.xml: give a machine a short, curated map instead of making it infer your site's shape from navigation and links.
Being straight about the state of adoption: it is fetched today mainly by coding agents and MCP clients such as Cursor and Claude Code, rather than by the big answer engines. No major search or answer engine has confirmed it as a ranking or retrieval input. We wrote up the evidence in our review of whether llms.txt affects Google Search, and the honest summary is that it is a two-minute hedge, not a growth lever.
The other two files are different: they do something today. AI crawler directives in robots.txt are honoured by the major operators and are the actual mechanism for deciding who may read your site and for what. The noai meta tags are the page-level version of the same choice.
If you want the part of this that moves visibility, it is not any of these three files - it is whether your pages are readable and well-described in the first place. Site Pulse grades that, and Schema Audit checks the structured data engines lean on to understand a page.
Frequently asked questions
https://yourdomain.com/llms.txt - the same place robots.txt lives. The fuller variant goes alongside it as llms-full.txt.robots.txt. If none of those resolve, there is nothing to index from - publishing a sitemap first is worth doing on its own merits, and then this run will work./pricing while leaving your blog open.Build your three files in about a minute
Generate yours freeLLM Visibility Tools
Generate the three files that define how AI systems see your site - a content map, crawler permissions, and per-page directives.
llms.txt
A structured markdown index of your site's pages. Today it's fetched mainly by coding agents and MCP clients (Cursor, Claude Code) rather than answer engines - and it's a two-minute hedge for when they do adopt it. Read our evidence review. Also generates llms-full.txt with complete page text.
robots.txt
Per-crawler directives for 14 major AI bots. Allow all, block all, or pick exactly who gets in - with per-bot path control in Custom mode.
Meta tags
HTML <head> snippets using noai and noimageai to opt pages out of AI training datasets.
