llms.txt and llms-full.txt are two files from the same proposal that serve different needs. llms.txt is a concise Markdown map — site name, summary, and sections of links with short descriptions — meant as a lightweight index. llms-full.txt follows the same structure but inlines fuller descriptions and, for content sites, much more of the actual page text, so a model can ingest substantial context in a single request instead of following every link. Publish llms.txt for almost any site; add llms-full.txt when your content is text-heavy (docs, guides, references) and you want models to absorb it without extra fetches. Neither file is a proven ranking lever — both are optional content hygiene.
What are the key takeaways?
llms.txt and llms-full.txt solve different depth problems: one is a scannable index of 10–20 links, the other inlines fuller content for one-fetch ingestion as of 2026.
- llms.txt is a concise Markdown link map deployed at /llms.txt.
- llms-full.txt inlines fuller descriptions and page text at /llms-full.txt.
- Publish llms.txt on almost any site; add llms-full.txt when content is text-heavy (docs, guides, references).
- Both files come from the 2024 community proposal at llmstxt.org — not a proven citation lever.
- Generate both files free with the llms.txt generator from any public URL.
What does each file contain?
llms.txt is a concise index of typically 10–20 described URLs; llms-full.txt uses the same H2 sections but inlines fuller page text so a model can absorb context in one fetch, per the companion format at llmstxt.org (September 2024).
Both files share the Markdown skeleton from the Answer.AI proposal: an H1 site name, an optional blockquote summary, and H2 sections of links. llms-full.txt expands each entry with fuller descriptions and, for docs-heavy sites, substantive body text from the listed pages.
- llms.txt: concise index — name, summary, sections of described links.
- llms-full.txt: same structure, but with fuller descriptions and inlined page content.
- Both are Markdown and both live at the site root (/llms.txt, /llms-full.txt).
When should you publish llms-full.txt?
Publish llms-full.txt when your site is text-heavy (documentation, API references, knowledge bases) and you want models to ingest up to 20 high-value pages in one fetch without following every link.
For a small marketing site or portfolio, llms-full.txt adds limited value because there is not enough content to inline. Publishing only llms.txt is a reasonable, lower-maintenance choice in that case.
Keep the file focused: llms-full.txt can grow large quickly, so curate genuinely high-value pages rather than dumping your entire sitemap. That keeps maintenance manageable and respects model context limits documented at llmstxt.org.
How do you generate both files?
Generation follows four steps: discover key URLs, read each page title and description, group links into logical H2 sections, and render spec-style Markdown. llms.txt outputs short pointers; llms-full.txt includes fuller text for the same URLs.
Our free generator produces both from one public URL: it analyses up to 20 pages, groups them semantically, and returns deployment instructions. Review and trim before publishing — generation is a strong first draft, not a final answer. Jeremy Howard of fast.ai introduced the underlying convention in 2024.
Which file should you publish first?
Publish llms.txt first on almost every site because it is the lightweight index (typically 10–20 described URLs) defined at llmstxt.org since September 2024.
Add llms-full.txt only when your content is text-heavy enough to benefit from inlined page text — documentation sites, API references, and guide libraries are the strongest fit. Marketing sites with under 10 key pages rarely need the fuller edition.
Frequently asked questions
What is the difference between llms.txt and llms-full.txt?+
llms.txt is a concise Markdown index: site name, summary, and sections of links with short descriptions. llms-full.txt uses the same structure but inlines fuller descriptions and, for content sites, much more page text, so a model can ingest context in a single fetch.
Do I need to publish both files?+
No. llms.txt alone is fine for most sites. Add llms-full.txt when your content is text-heavy — documentation, references, guide libraries — and you want models to absorb the substance without fetching every page individually.
Can llms-full.txt get too big?+
Yes. Because it inlines page text it can grow large, so keep it focused on genuinely high-value pages rather than the whole site. That keeps it maintainable and respects the limited context a model will actually use.