Home › Tools › llms.txt Generator
llms.txt Generator
Build a valid llms.txt file — the plain-text index that tells AI crawlers what your site offers. Runs entirely in your browser. Paste, build, copy.
SerpPrism's llms.txt Generator is a free online tool that builds a valid llms.txt file — the plain-text index that tells AI crawlers what your site offers and which pages matter. No sign-up is needed and the generator runs entirely in your browser. It is for site owners who want their content described accurately when AI assistants answer questions about their topic. Paste your site name, a one-line summary, and your pages or tools. Get a properly formatted llms.txt you can drop at your domain root. Nothing is uploaded.
How to use it
- Fill in your site name and a one-line summary that says what the site does, not what it wants to rank for.
- Add one entry per page or tool, in the format
Title | /path | description. - Copy the result and save it as
llms.txtat your domain root, next torobots.txt.
What llms.txt is actually for
llms.txt is a plain-text file at your domain root that describes what your site offers, written to be read by language models rather than by people. It is a proposal rather than a standard — no major crawler has committed to obeying it — but it costs one small file and it is the only place where you get to describe your own site in your own words.
The practical value is not ranking. It is correction. A model that has only seen scraped fragments of your site will guess what it does. A well-written llms.txt replaces that guess with your own description.
Why relative paths are the default
Relative paths keep the file valid if you change domain, move from a subdomain to the root, or serve the same content over several hostnames. Absolute URLs break in all three cases and are the most common way these files silently go stale.
Switch to absolute URLs only if you are publishing the file somewhere that is not your own domain root, where a relative path has nothing to resolve against.
Writing entries that are actually useful
The description field is where most of these files fail. 'Home', 'About us', and 'Our services' tell a reader nothing it did not already know. Write what the page does: 'Convert SubRip subtitles to WebVTT, preserving timing and cue numbering.'
Be specific about constraints, because they are the thing a reader cannot infer. If a tool only handles certain input formats, or if output is approximate, say so in the description rather than leaving it to be discovered.
Order matters less than completeness, but put the pages you would want someone to see first at the top. A reader that truncates will keep the head of the file.
A worked example: a five-page site's llms.txt
A small subtitle-tools site fills in its name — 'SubSync Tools' — and one summary line: 'Free subtitle utilities that run in your browser.' Then five entries, one per line, in the Title | /path | description format: SRT to VTT, Merge Subtitles, Shift Subtitles, Subtitle Checker, and the About page.
The output follows the proposal's format exactly: a # SubSync Tools heading, the summary as a blockquote line starting with >, a ## Tools heading, and one markdown link per entry — - [SRT to VTT](/tools/srt-to-vtt): Convert SubRip subtitles to WebVTT. The description is optional; an entry without one is still valid, just less useful.
Two details worth knowing before you paste. First, a row that is not in the three-part format is skipped, and the generator tells you how many lines it skipped — so a pasted list with a stray blank line or a missing pipe does not silently lose entries. Second, the section heading is yours to choose: 'Tools' fits a utility site, 'Docs' fits a documentation site, and the wrong heading is the kind of small inaccuracy that makes a machine reader trust the file less.
What this file will not do
It will not improve your rankings, and no search engine currently reads it as a ranking signal. Treat it as documentation for machines, not as an SEO tactic.
It also does not replace robots.txt. If you want a crawler to stay out, that is still robots.txt. llms.txt describes; robots.txt permits.
Questions
Is llms.txt an official standard?
No. It is a community proposal that several AI companies have said they are aware of. No major crawler has formally committed to it. It is cheap to publish and harmless if ignored.
Where exactly does the file go?
At the domain root — https://yoursite.com/llms.txt, the same place as robots.txt. A file at any other path will not be found.
How is this different from robots.txt?
robots.txt controls whether a crawler may fetch pages. llms.txt describes what the site contains. They do different jobs and you can publish either without the other.
Should I list every page?
No. List the pages that represent what your site does. A file with two hundred entries is worse than one with fifteen useful ones, because the signal gets lost.
Do AI crawlers like ChatGPT actually read llms.txt?
No major AI company has formally committed to it, so treat it as cheap insurance rather than a ranking lever. The file costs minutes to publish, uses the llms.txt proposal format correctly, and gives any crawler that does look a clean, curated map of your site. The generator builds the file in that format, with relative paths by default.
What should I put in my llms.txt file?
Your homepage plus the pages that represent what the site does — main tools, key guides, an about page — each with a one-line description written for someone who has never seen the site. Fifteen useful entries beat two hundred exhaustive ones, because the file's job is signal, not inventory.
What is the difference between llms.txt and sitemap.xml?
A sitemap lists every indexable URL for search crawlers, with no explanation. llms.txt is a short, human-readable shortlist with descriptions, written for AI systems. They live side by side at the domain root and neither replaces the other.
Should llms.txt list pages that are noindex?
No. If a page should not be indexed, it should not be in the file either. The file is a shortlist of what you want found, not an inventory.
How often should I update the file?
When the site changes meaningfully: a new tool, a removed page, a renamed section. A stale file is worse than none, because it describes a site that no longer exists.
Related tools
Schema Markup Generator
Generate valid JSON-LD for Article, FAQ, HowTo, Product, BreadcrumbList and Organization.
Meta Tag Generator
Generate clean page title, meta description, canonical, Open Graph and Twitter card tags.
robots.txt Tester
Paste a robots.txt and test any URL against any user-agent.
Related guides
llms.txt Adoption: 22 of 78 Big Sites
Half of 78 well-known sites return a clean 404 for /llms.txt. Of the 22 that serve one, 11 hide behind a redirect and 4 break their own heading.
How AI Search Engines Choose What to Cite
AI search engines cite pages they can find, understand, and trust. Here is what makes a page citable, and how this site is built to be one. No tricks involved.