Using LLMS.txt
llms.txt is a new and emerging standard.
HelpGuides provides native support for the llms.txt standard, so AI agents, LLMs and developer tools (like Cursor, Perplexity and Claude) can find and understand your documentation efficiently.
By providing a machine-readable map of your content, it removes the "noise" of HTML headers and navigation menus, so AI models can focus on the content they need to give accurate answers.
All articles published are automatically available in Markdown format.
Available Endpoints
- llms.txt at
https://YOUR-DOMAIN/llms.txt: a short index with your site's name and description, a link tollms-full.txt, and the articles you've chosen to feature, each with its meta description. - llms-full.txt at
https://YOUR-DOMAIN/llms-full.txt: the full text of every published article in one Markdown file, with each article's URL, last updated date and description. Ideal for giving an LLM your whole library in a single request. It's refreshed at most every three hours.
A generated llms.txt looks like this:
Choose the articles in llms.txt
Feature 3 to 10 of your most important articles. To feature one, open it in the editor and click the star icon above the title; click it again to remove it. Starred articles are included automatically, as long as they're published.
To see which articles are featured, open AI Settings and click the llms.txt tab. It lists each featured article and links to your live file. See AI Settings.
Recommendedllms.txt is useful for discovery. If you know an LLM or agent will use your HelpGuides content, connect it with Model Context Protocol instead.
See Model Context Protocol. Your site's robots.txt asks search engine crawlers to skip llms-full.txt and the Markdown versions of your articles.
Benefits for AI Workflows
- Reduced token usage: Serving Markdown instead of heavy HTML keeps AI interactions within context limits and makes them faster.
- Improved accuracy: Only published articles are included, so AI models don't learn from drafts or outdated content.
- Tooling support: Works with the Cursor @Docs feature. Point Cursor at your documentation URL and it finds the
llms.txtfile to build a local index of your guides.
Related: Viewing in Markdown, Supporting AI Crawlers with ai.txt.