llms.txt Generator & Validator
Draft an llms.txt from your sitemap, then validate it against the spec.
What is llms.txt, and what does this tool do?
llms.txt is a plain markdown file placed at the root of a website, at /llms.txt, that gives large language models a short, curated map of the site. It was proposed by Jeremy Howard in September 2024 and is documented at llmstxt.org. The idea: a model with a limited context window should not have to wade through menus and scripts to find your key pages. A compact, annotated list is easier to use.
This tool has two parts. The Generate tab builds a valid file from a form: site name, one-line summary, an optional details paragraph and any number of sections, each holding links with a title, URL and optional note. It can also auto-draft a starting file from your domain by reading the homepage title, meta description and sitemap.xml. The markdown output updates live as you type, and you can copy it or download it as llms.txt.
The Validate tab checks an existing file. Paste the text, or enter a domain and the tool fetches https://yourdomain/llms.txt, then tests it against the llmstxt.org format and reports errors, warnings and the HTTP response details.
A related convention is llms-full.txt, a single file containing the full text of your key pages in markdown.
How to create and validate an llms.txt file
- 1
Start from your domain or a blank form
Enter your domain to auto-draft, and the tool pulls your homepage title and description and suggests links from sitemap.xml. Or fill in the site name and summary yourself. Prune the draft to what is useful.
- 2
Write a precise summary
The one-line summary becomes the blockquote under the title. State what the site or company is, who it serves and what someone will find here, in plain words a model can quote accurately.
- 3
Organize links into sections
Create H2 sections such as Docs, Products, Guides or Policies. For each link, add a descriptive title, the absolute URL and a short note that explains when that page is the right one to read.
- 4
Use the Optional section for secondary pages
Put nice-to-have links, such as the archive, changelog or background reading, under the special Optional section. The spec says tools can skip it when they need a shorter context.
- 5
Download and upload to your site root
Download the file as llms.txt and place it at the root of your domain so it loads at https://yourdomain/llms.txt. It should not sit in a subfolder.
- 6
Validate the live file
Switch to the Validate tab, enter your domain and fix anything flagged, especially a non-200 status or a content type other than text/plain or text/markdown.
Who uses an llms.txt generator
Documentation and developer sites
API references, SDK guides and quickstarts are where llms.txt is most used today, because developers paste documentation links into coding assistants and agents that look for the file.
SaaS and product companies
Point models to accurate pages on features, pricing, integrations and limits, so an assistant reading your site has an authoritative source rather than an outdated third-party review.
Publishers and content-heavy sites
Highlight cornerstone guides and category hubs instead of thousands of individual posts.
Agencies and consultants
Generate a clean file for each client in minutes, then validate it after deployment as part of a technical SEO or AI search readiness audit.
Validation rules, and how llms.txt fits with robots.txt and sitemap.xml
The validator checks the structure set out at llmstxt.org. The file must start with exactly one H1 containing the site or project name, as the first content. A blockquote summary directly under it is recommended. Sections then use H2 headings, each containing a markdown list of links in the form - [name](url): notes. The tool flags relative URLs, since links should be absolute, H3 or deeper headings, links outside lists, a misplaced Optional section and oversized files.
For a live file, it also checks delivery: the file should return HTTP 200 at the domain root, with a text/plain or text/markdown content type.
llms.txt does a different job from the files it is often compared with. robots.txt controls access: which crawlers may fetch which paths. sitemap.xml is a complete list of indexable URLs for search engines, without context. llms.txt grants and denies nothing; it is a curated, human-readable guide that explains which pages matter and why.
Be realistic about impact. llms.txt is still a proposal. Major AI providers, including OpenAI, Google and Anthropic, have not committed to reading it when crawling or answering questions, and there is no evidence that it affects rankings or citations. Some developer tools and agents use it. Treat it as a low-cost, forward-looking addition, not a replacement for crawlable pages, clear content and a sound robots.txt.
Frequently asked questions
Is the llms.txt generator and validator free?
Yes, both the generator and the validator are free, with no account and no limit on how many files you create or check. You can auto-draft from a domain, edit sections, copy or download the result and validate live files as often as you need. The file you produce is yours to use on any personal, client or commercial site.
What does the tool fetch from my site?
It fetches only public files. Auto-draft reads your homepage title and meta description and your sitemap.xml to suggest links. Validate requests https://yourdomain/llms.txt and records the HTTP status, content type and file contents. Nothing on your site is changed, and text you paste into the validator is checked for your session rather than published or shared.
Where should I put my llms.txt file?
Put llms.txt at the root of your domain so it loads at https://yourdomain/llms.txt, the same level as robots.txt. Serve it with an HTTP 200 status and a text/plain or text/markdown content type. Avoid redirects to other paths. If you publish separate documentation subdomains, each one can have its own llms.txt describing that site.
Do ChatGPT, Gemini and Claude actually read llms.txt?
There is no public commitment from OpenAI, Google or Anthropic that their crawlers or assistants read llms.txt. It remains a community proposal. Some developer tools, documentation platforms and AI agents do use it, and an assistant may read it when a user points to it directly. Add it because it is cheap and harmless, not because it guarantees citations.
What is the difference between llms.txt and llms-full.txt?
llms.txt is a short index of links with notes, while llms-full.txt contains the full text of those pages in one markdown file. The index lets a tool decide what to read; the full version lets it load everything at once. llms-full.txt makes most sense for documentation sites and can become large, so keep it current if you publish one.
Does llms.txt replace robots.txt or my XML sitemap?
No, llms.txt replaces neither file. robots.txt controls which crawlers may access which paths, and sitemap.xml lists every indexable URL for search engines. llms.txt is a curated guide to your most useful pages and has no access-control effect. Keep all three, and make sure robots.txt does not block the pages your llms.txt points to.
Built and reviewed by Umer Anees, SEO consultant.
Related tools
More AI Search tools →AI Crawler Checker
See which AI bots — GPTBot, ClaudeBot, PerplexityBot and 19 more — can crawl your site.
AI Search
Word Counter
Count words, characters, sentences and reading time as you type.
Text
Case Converter
Switch text between UPPER, lower, Title, Sentence, camelCase and more.
Text
Meta Tag Generator
Write title, description, Open Graph and Twitter tags with a live SERP preview.
SEO