Give AI assistants a clean map of your site. Enter your domain, we read your sitemap and build a valid llms.txt you can curate, copy, and download. Free, no sign-up.
Enter your website. We read your sitemap.xml and each page's title and description, then let you pick and edit what goes in the file.
We only read public pages, no login required. Big sites are capped so the tool stays fast.
More free tools to cover every angle of your technical and on-page SEO.
Paste your content and check keyword density instantly. Optimize without over-stuffing.
Use Tool →Analyze your content readability with Flesch Reading Ease and grade-level scores.
Use Tool →Check if your page title fits Google SERP limits and preview how it looks in search results.
Use Tool →Generate perfectly formatted title and meta description tags for any page.
Use Tool →Build valid FAQ JSON-LD schema markup to unlock rich results in Google search.
Use Tool →Create Open Graph and Twitter Card meta tags to control how your pages look when shared.
Use Tool →Turn any title into a clean, SEO-friendly URL slug in seconds.
Use Tool →Build a valid robots.txt file with custom rules for any crawler.
Use Tool →Analyze your heading hierarchy, catch missing H1s, and fix structural SEO issues.
Use Tool →Count words, characters, sentences, paragraphs, and get reading time estimates instantly.
Use Tool →How It Works
No account, no sign-up, and no download gate. Enter your site, curate the pages that matter, and get a valid llms.txt in under a minute.
Paste your domain and hit Fetch Pages. The tool reads your sitemap.xml, the machine-readable list of all your URLs, and pulls each page title and meta description. No sitemap? It falls back to your homepage links.
Toggle pages on or off, edit titles and one-line descriptions, rename and reorder sections, and mark secondary groups as Optional. A good llms.txt is curated, not a dump of every URL you have.
Generate a spec-valid llms.txt, then copy it or download the file. Save it as llms.txt and upload it to your site root so it is reachable at yourdomain.com/llms.txt. Free, no account required.
The Format
The format is deliberately simple: one H1 title, an optional summary, then H2 sections that each hold a markdown list of links with short descriptions.
Example llms.txt
# Acme Analytics > Privacy-first web analytics for small teams. ## Docs - [Quickstart](https://acme.com/docs/start): Install and see data in 5 minutes - [API reference](https://acme.com/docs/api): Endpoints, auth, and rate limits ## Guides - [Migrating from GA4](https://acme.com/guides/ga4): Step-by-step import ## Optional - [Changelog](https://acme.com/changelog): Release history
The only required element is the H1 title at the top. Everything else is optional, but a short summary in a blockquote and a few well-organized sections make the file far more useful to a model trying to understand your site quickly.
Each link is a standard markdown list item. Add a colon and a short note after the URL to explain what the page covers. Those descriptions are the highest-value part of the file, they are what a model reads to decide which page answers a given question.
The Optional section is special. Its name is reserved: links placed there can be skipped by a model when it needs a shorter context. Use it for secondary pages like changelogs, legal, or archives.
Element Reference
Use this as a quick reference for what belongs in the file and which parts are required.
| Element | Status | What It Does |
|---|---|---|
| # Title | Required | A single H1 with your site or project name. This is the only mandatory line in the whole file. |
| > Summary | Recommended | A blockquote right after the title with a short, plain summary of what your site is and who it is for. |
| ## Section | Optional | H2 headings that group related links, for example Docs, Blog, or Products. Order them by importance. |
| - [name](url) | Per section | A markdown link list item. Add a colon and a short note after the link to describe what the page covers. |
| ## Optional | Special | A reserved section name. Links placed here can be skipped by a model when a shorter context is needed. |
| llms-full.txt | Companion | A separate, larger file that inlines the full page content rather than just linking to it. This tool builds the linked llms.txt. |
Based on the llms.txt specification published at llmstxt.org (proposed 2024).
What It Is And Isn't
llms.txt is genuinely useful and genuinely low-cost, but it is easy to over-promise. Here is a straight read on what it does and does not do.
llms.txt was proposed by the community in 2024. Major AI providers have not confirmed they read it or that it affects rankings. Treat it as a clean, low-cost way to structure your site for AI, not a guaranteed traffic lever.
Publish it because it is cheap and tidy, not for promised rankingsrobots.txt controls what crawlers may access. sitemap.xml lists every URL for search engines. llms.txt is a curated, human-readable highlight reel written in markdown for language models. The three complement each other.
Curated highlights, not access rules or a full URL dumpListing all 4,000 of your URLs defeats the purpose. The value is pointing a model at your best, most representative pages with clear descriptions. Trim aggressively and describe each link well.
Fewer, well-described links outperform an exhaustive listThe file must be reachable at yourdomain.com/llms.txt to be discovered. Uploading it to a subfolder or leaving it in your CMS drafts means nothing can find it.
Must resolve at /llms.txt on your root domainA llms.txt is a snapshot. When you launch important pages, restructure your docs, or retire products, the file drifts out of date. Regenerate it periodically so the map still matches the territory.
Refresh whenever you ship significant new contentAnything you list in llms.txt is readable by anyone who opens the file. Only include pages you are happy to have surfaced. Never list private, staging, or gated URLs.
Public file: list only pages you want seenGet More From It
A great llms.txt is curated, well-described, and kept current. These tips help you build one that actually helps AI represent your site. All Common Ninja widgets are free to start.
Put your most important sections first: what you do, your core products or docs, and your best explainer content. Models weigh earlier context more heavily, so order matters.
The note after each link is your chance to add context. Skip jargon and internal names. A one-line description of what the page actually helps someone do is far more useful than the raw title.
Terms, privacy, changelogs, and niche pages are legitimate but rarely the point. Mark those sections Optional so a model can skip them when it needs a tighter context window.
FAQ accordions turn your knowledge into clean question-and-answer blocks that assistants can lift accurately. Pair rich FAQ pages with a llms.txt that points right at them.
Try Accordion widget →Tab widgets keep several related content sections on one URL. That gives a model more context per link in your llms.txt without spreading thin content across many pages.
Try Tabs widget →Comparison tables are exactly the structured, high-intent content AI assistants reach for. List your comparison pages prominently so they get pulled into answers.
Try Comparison Tables widget →Treat llms.txt like code. Store it in your repo next to robots.txt, review changes in pull requests, and redeploy it with your site so it never silently rots.
A single malformed link line can break the structure. Use the Validate tab above to check your H1, summary, section headings, and link formatting before you upload the file.
AI & SEO Glossary
llms.txt sits inside a broader set of files and practices for search and AI. Here is how the key pieces relate and when each one matters.
| Term | Definition | Format | When to Use |
|---|---|---|---|
| llms.txt | A markdown file at your site root that gives AI models a curated, readable map of your most important pages with short descriptions. | yourdomain.com/llms.txt | Helping AI assistants understand and represent your site accurately |
| llms-full.txt | A companion file that inlines the actual page content rather than just linking to it, giving a model everything in one fetch. Larger and heavier to maintain. | yourdomain.com/llms-full.txt | When you want models to have full content without following links |
| GEO | Generative Engine Optimization: the practice of structuring content so AI assistants and answer engines cite it correctly. The AI-era counterpart to SEO. | Discipline, not a file | Planning content for AI answer engines alongside search |
| robots.txt | A plain text file that tells crawlers which URLs they may or may not access. It controls crawling, not how AI summarizes you. | yourdomain.com/robots.txt | Controlling crawler access across your site |
| XML Sitemap | A machine-readable file listing all important URLs on your site so search engines can discover them. llms.txt is built from it, but curated down. | yourdomain.com/sitemap.xml | Ensuring every important page is discoverable by search engines |
From the Blog
Dig deeper into optimizing your content for search engines and AI answer engines.
In this article, we are going to discuss SEO, explain why it’s important to the success of a website, and suggest ways t...
Read article →In this article, we are going to discuss font pairing, and why it’s important to web design ...
Read article →In this article, we are going to discuss the top 6 Airbnb Reviews widgets for your website. ...
Read article →In this article, we are going to discuss AI, how it revolutionizes the industry of web design and discuss the future of ...
Read article →In this blog post, we will learn how to collect emails with Next.js, Mailchimp, and Chakra UI. ...
Read article →In this article, we will look at some important SEO factors to consider when building a website, for the purpose of incr...
Read article →