llms.txt
Every Jamdesk site generates llms.txt and llms-full.txt automatically. AI tools use these files to understand your documentation.
If you want AI tools like ChatGPT, Claude, or Copilot to give accurate answers about your product, they need structured access to your docs, not just whatever made it into their training data.
Every Jamdesk site generates llms.txt and llms-full.txt following the llmstxt.org spec. AI tools read these files instead of crawling individual pages.
Google now audits llms.txt as part of Lighthouse's agentic browsing checks. Sites that publish a valid llms.txt are more discoverable to AI agents — and increasingly, to Google itself when ranking content for AI-powered answers. Jamdesk gives you this for free.
Check your score. See how agent-ready any docs site is with the free AI Score tool — publishing a valid llms.txt is one of the first things it checks for. There's also an AI Score Chrome extension to grade sites as you browse.
What Jamdesk Generates
| File | Content |
|---|---|
llms.txt | Page titles, descriptions, and URLs (a structured table of contents) |
llms-full.txt | Complete documentation content in a single file |
Jamdesk generates both at build time and serves them from the same CDN as your docs.
Verify Your Files
Check that your files exist after your first build:
If your docs are at the root of your domain (e.g., docs.acme.com or acme.jamdesk.app):
curl https://docs.acme.com/llms.txt
curl https://docs.acme.com/llms-full.txtFile Format
The llms.txt file lists every page with its title, description, and URL, grouped into sections that mirror your navigation:
# Your Project Documentation
> Documentation for Your Project
## Get Started
- [Getting Started](https://your-project.jamdesk.app/getting-started): Set up your first project in 5 minutes
- [Configuration](https://your-project.jamdesk.app/configuration): Configure your project settings
## API Reference
- [Authentication](https://your-project.jamdesk.app/authentication): How to authenticate API requestsThe llms-full.txt file contains the complete Markdown content of every page, concatenated with page boundaries marked by headings.
Structure
llms.txt follows the llmstxt.org proposal: an H1 title,
a blockquote summary, and your navigation tabs and groups as ## sections of
Markdown links.
Multilingual sites get one index per language. The root llms.txt lists your
default language and links each translated index at the end — for example
/fr/llms.txt for French. Each language file links back to its siblings.
Agent directive on every page
Every page also carries an invisible, screen-reader-silent note for AI agents
pointing at llms.txt, and every Markdown export starts with a blockquote
linking the index. Agents that land on your HTML find the Markdown path
without crawling.
How It's Built
- Generated at build time alongside your HTML
- Served from CDN with the same cache policy as your docs
- Updates automatically on every build
- No configuration needed; all pages are included by default
Turning Off llms.txt
llms.txt and llms-full.txt are published by default. To stop generating them — for example, if you don't want AI tools ingesting your content — set seo.ai.llmsTxt to false in your docs.json:
{
"seo": {
"ai": {
"llmsTxt": false
}
}
}On your next build, Jamdesk skips both files and the live /llms.txt and /llms-full.txt URLs return 404.
AI ingestion and search indexing are separate controls. seo.ai.llmsTxt governs only the llms.txt/llms-full.txt files that AI tools read. It does not change how search engines index your site — that's controlled by robots metadata and per-page noindex. A page can be indexed by Google while excluded from AI ingestion, or vice versa.
AI Crawlers
Jamdesk's default robots.txt allows all major AI crawlers (Claude, ChatGPT, Copilot, Gemini). Your documentation is accessible to AI tools out of the box.
sitemap.xml lists URLs for search engines to crawl and index. It doesn't include any content, just links and metadata like last-modified dates.
llms.txt is designed for AI models. It includes page titles, descriptions, and (in llms-full.txt) the actual content. AI tools can read the full file to understand your documentation without making multiple HTTP requests.