Skip to main content
Free Tools

llms.txt generator: create a spec-compliant llms.txt (free)

Paste your key pages and generate an editable, spec-compliant llms.txt and llms-full.txt - then copy or download. No crawling, no signup.

No signup requiredClient-side only - no data sentEditable before you download

Generate your llms.txt

Paste your key pages — everything runs in your browser. Nothing is sent or crawled.

Becomes the H1 at the top of the file.

Becomes the > blockquote under the title.

One per line. Format: Title | https://url | short description (description optional). Or paste a sitemap URL list — we'll use the URLs.

0 pages parsed

How should sections be grouped?

Quick answer

llms.txt is a community-proposed Markdown file at /llms.txt that gives AI models a curated map of your site - a site name, a one-line summary, and sectioned links with short descriptions. A companion llms-full.txt inlines fuller content. Proposed by Jeremy Howard (Answer.AI, 2024), it complements robots.txt and your sitemap. Treat it as low-risk hygiene, not a proven ranking lever. Paste your pages above to generate both files, edit them, and download.

Key takeaways

  • llms.txt is a Markdown map for AI models, placed at your site root.
  • Structure: H1 site name → blockquote summary → H2 sections of links with descriptions.
  • llms-full.txt inlines fuller content for models that prefer it.
  • It's a community proposal, not an official standard - and engine support is inconsistent.
  • Fix crawlability and server-rendered HTML first; llms.txt is hygiene, not magic.

What is llms.txt?

llms.txt is a plain Markdown file you place at your site root so it resolves at /llms.txt. It hands AI models a curated, machine-readable map of your most important pages: a title, a one-line summary, and grouped links with short descriptions. It was proposed by Jeremy Howard of Answer.AI in September 2024 as a way to give language models clean context at inference time - but it's a proposal, not a W3C or IETF standard. It's real and emerging: adopters include Vercel, Next.js, Stripe, and Anthropic. Support across AI engines is still inconsistent and largely undocumented, so set expectations accordingly.

The llms.txt format (with example)

The format is deliberately simple Markdown: an # H1 with your site name, a > blockquote one-line summary, then ## H2 sections, each containing a list of links with an optional short description after a colon.

# Site Name
> One-sentence summary of what the site/product is.

## Docs
- [Page title](https://example.com/page): short description

## Guides
- [Guide title](https://example.com/guide): short description

The optional llms-full.txt uses the same header but inlines fuller content under each page heading instead of a single link line - useful for models that prefer more context in one file:

## Page title
https://example.com/page

A fuller paragraph of content describing this page in detail.

How to create an llms.txt file

Manually: list your most important pages, write the H1 site name and a one-line summary, group the links into sections with short descriptions, and save the file at your root so it resolves at /llms.txt. Or simply paste your URL list or sitemap into the generator above, pick auto-grouping or a single section, and edit the result before downloading.

llms.txt vs robots.txt vs sitemap

FileSays to machinesPurpose
robots.txt"You may/may not crawl these paths"Access control
sitemap.xml"Here is every URL"Discovery / completeness
llms.txt"Here's what matters and what it means"Curated context for AI models

Does llms.txt improve AI visibility?

Honestly: there's no public, controlled evidence that llms.txt measurably increases AI citations, and engine support is inconsistent and undocumented. It's cheap, low-risk hygiene - but crawl access and clean, server-rendered HTML matter far more to whether AI engines can read and cite you. Fix those first. Add llms.txt because it costs almost nothing and can't hurt, not because it's a magic lever.

Who benefits most

Documentation-heavy sites, sites with many distinct sections, frequently changing content, and API references benefit most - they have lots of structure worth summarizing for a model. For a small marketing site the upside is modest, but the cost is near zero, so it's still reasonable hygiene.

How to deploy

Place the file at your web root so it resolves at https://yourdomain.com/llms.txt (and /llms-full.txt for the fuller version). Re-generate when your key pages change so the map stays accurate.

Frequently asked questions

What is an llms.txt file?
A Markdown file at /llms.txt that gives AI models a curated map of your most important pages with short descriptions.
How do I create an llms.txt file?
List key pages, add an H1 site name and one-line summary, group links into H2 sections with descriptions, and place it at your root - or use the generator above.
What's the difference between llms.txt and llms-full.txt?
llms.txt is a concise link map; llms-full.txt inlines fuller page content for models that prefer more context.
Does llms.txt help SEO or AI rankings?
There's no controlled evidence it boosts citations; treat it as low-risk hygiene, not a ranking lever.
Is llms.txt an official standard?
No - it's a 2024 community proposal by Jeremy Howard (Answer.AI), not a W3C or IETF standard.
How is it different from robots.txt?
robots.txt controls crawler access; llms.txt provides curated meaning and priorities for AI models.
Where do I put the file?
At your domain root, so it loads at /llms.txt (and /llms-full.txt).
Who should bother with llms.txt?
Documentation- and content-heavy sites benefit most; small sites gain little but lose nothing.

Treat llms.txt as hygiene, not a growth hack

The most useful framing for llms.txt is the most honest one: it's low-risk hygiene, not a proven ranking lever. A clean, curated file can only help a model understand your site - but it won't rescue a site that AI crawlers can't read in the first place. If your content is locked behind heavy client-side rendering, blocked in robots.txt, or buried under thin pages, llms.txt changes nothing. Get the fundamentals right, then add llms.txt as a finishing touch.

Glossary

TermMeaning
llms.txtMarkdown file at /llms.txt giving AI models a curated link map of your site.
llms-full.txtCompanion file that inlines fuller page content instead of just links.
MarkdownLightweight plain-text formatting syntax used for both files.
robots.txtFile controlling which paths crawlers may or may not access.
sitemap.xmlMachine-readable list of every URL on your site for discovery.
GEO / AEOGenerative / Answer Engine Optimization - getting cited by AI answer engines.
Inference-timeThe moment a model generates a response, when it may read context like llms.txt.
CrawlabilityHow easily bots can reach and read your pages.
Server-rendered HTMLHTML delivered fully formed by the server, readable without running JavaScript.

Related tools

Last updated June 2026

Launch Faster

Ready to ship your next product?

Tell us what you're building. Senior engineers will scope, plan, and start delivering your product with production-ready architecture - fast.

Talk to real engineers
Clear scope in one call
No obligation