llms-full.txt explained (vs llms.txt)
By Abhijay Tondak, Founder · Updated July 2, 2026 · 5 min read
llms.txt is a proposed standard file that gives AI crawlers a curated index of your most important pages (like a sitemap tuned for LLMs), while llms-full.txt goes further by including the full text content of those pages in one file, so an AI system can ingest your key content directly. Both are emerging conventions, not universally supported - publish them as a low-cost, forward-looking signal, but treat them as complements to (not replacements for) crawlable pages and a real sitemap.
Key takeaways
- llms.txt = a curated index of your key pages for AI crawlers (LLM-tuned sitemap).
- llms-full.txt = goes further, including the full text content in one file.
- Both are emerging conventions, not yet universally supported.
- Low-cost, forward-looking to publish - but complements, not replaces, crawlable pages + sitemap.
- Keep them accurate and current, or they mislead more than help.
What llms.txt and llms-full.txt are
llms.txt is a proposed convention: a plain-text file at your site root that gives AI crawlers a curated, prioritized list of your most important pages with short descriptions - essentially a sitemap tuned for LLMs, pointing them at your best content. llms-full.txt takes it further: instead of just linking pages, it includes their full text content in one file, so an AI system can ingest your key content directly without crawling each page.
How they differ from a sitemap
A sitemap lists all your URLs for search-engine discovery. llms.txt is curated and descriptive - it highlights your best pages for AI specifically, with context. llms-full.txt goes beyond linking to actually bundling the content. Think of it as a spectrum: sitemap (all URLs) → llms.txt (curated key pages + descriptions) → llms-full.txt (curated pages + their full text).
Should you publish them?
They're low-cost and forward-looking, so publishing llms.txt is reasonable as a signal - but be realistic: these are emerging conventions with uneven support, not guaranteed to be read. Treat them as a complement to the fundamentals (crawlable pages, a real sitemap, clean structure), never a replacement. llms-full.txt is more effort (bundling content) and even less established - worth it mainly if you specifically want to offer your content in an ingestible form.
- Publish llms.txt: low effort, forward-looking, points AI at your best pages.
- Consider llms-full.txt if you want to offer full content in one ingestible file.
- Never rely on either instead of crawlable pages + a standard sitemap.
Keep them accurate
An outdated or inaccurate llms.txt/llms-full.txt is worse than none - it points AI at stale or wrong content. If you publish them, keep them current as your content changes (ideally generate them from your live content so they can't drift). Accuracy is the whole value; a stale index misleads.
Frequently asked questions
What's the difference between llms.txt and llms-full.txt?
llms.txt is a curated index of your key pages (links + descriptions) for AI crawlers - a sitemap tuned for LLMs. llms-full.txt goes further by including the full text content of those pages in one file, so an AI system can ingest your content directly.
Are llms.txt files actually used by AI engines?
They're an emerging convention with uneven support - not guaranteed to be read. Publish llms.txt as a low-cost, forward-looking signal, but treat it as a complement to crawlable pages and a real sitemap, never a replacement.
Should I publish llms-full.txt?
Consider it if you specifically want to offer your key content in one ingestible file - but it's more effort (bundling content) and even less established than llms.txt. For most sites, a good llms.txt plus crawlable pages is enough.
How do I keep these files from going stale?
Generate them from your live content so they can't drift, and update as content changes. An outdated llms.txt is worse than none - it points AI at stale or wrong content. Accuracy is the entire value.
Put this into practice — free.
Get your free AI-visibility audit and see where engines find you today.
More from this topic
Keep building your expertise with related GEO content in the same cluster.
Structured data (JSON-LD) for AI search
Structured data helps AI engines understand and cite your pages. Here are the JSON-LD schema types that matter for AI search and how to implement them.
ReadHow to write a TL;DR that gets cited
A citable TL;DR answers the page's core question in 1-3 self-contained sentences at the top. Here's how to write one AI answer engines will lift verbatim.
ReadWhy original data and statistics win AI citations
Original statistics and data give AI answer engines something concrete and attributable to cite. Here's why proprietary data outperforms recycled claims in GEO.
Read