{"id":2133,"date":"2026-07-11T08:50:44","date_gmt":"2026-07-11T08:50:44","guid":{"rendered":"https:\/\/crowdreply.io\/blog\/?p=2133"},"modified":"2026-09-06T12:33:10","modified_gmt":"2026-09-06T12:33:10","slug":"what-is-llms-txt","status":"publish","type":"post","link":"https:\/\/crowdreply.io\/blog\/what-is-llms-txt\/","title":{"rendered":"What is llms.txt? And Does it Work?"},"content":{"rendered":"\n<div class=\"cr-article gb-element-637ef531\">\n<style>.cr-tblwrap{overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%}.cr-tblwrap .cr-table2{min-width:100%}.cr-tblwrap .cr-avc-3{min-width:560px}.cr-tblwrap .cr-avc-4{min-width:720px}.cr-tblwrap .cr-avc-5{min-width:880px}.cr-tblwrap .cr-avc-6{min-width:1040px}.cr-tblwrap .cr-avc-7{min-width:1200px}.cr-tblwrap .cr-avc-8{min-width:1360px}.cr-avc-2 .cr-tr2{grid-template-columns:1.4fr 1fr}.cr-avc-3 .cr-tr2{grid-template-columns:1.3fr 1fr 1fr}.cr-avc-4 .cr-tr2{grid-template-columns:1.3fr 1fr 1fr 1fr}.cr-avc-5 .cr-tr2{grid-template-columns:1.3fr 1fr 1fr 1fr 1fr}.cr-avc-6 .cr-tr2{grid-template-columns:1.3fr repeat(5,1fr)}.cr-avc-7 .cr-tr2{grid-template-columns:1.3fr repeat(6,1fr)}.cr-avc-8 .cr-tr2{grid-template-columns:1.3fr repeat(7,1fr)}<\/style>\n\n\n\n<div class=\"cr-callout gb-element-8da1a99b\">\n<div class=\"cr-callout-head gb-element-34db4a82\">\n<p class=\"cr-icon-24 cr-icon-24 gb-text-1024d778\"><span class=\"gb-shape\"><svg width=\"18\" height=\"18\" viewBox=\"0 0 18 18\" fill=\"none\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M11.4234 6.6947C11.033 6.32491 10.7819 5.83197 10.7124 5.2988L10.3497 2.5241L7.89266 3.8615C7.42025 4.11892 6.87357 4.20569 6.34466 4.1072L3.59426 3.5942L4.10726 6.3446C4.20575 6.87351 4.11898 7.42019 3.86156 7.8926L2.52416 10.3496L5.29886 10.7123C5.83171 10.7821 6.3243 11.0331 6.69386 11.4233L8.61806 13.4546L9.82046 10.9283C10.0513 10.4428 10.4422 10.0516 10.9275 9.8204L13.4547 8.618L11.4234 6.6947ZM11.4459 11.7014L9.45416 15.8864C9.41648 15.9655 9.36011 16.0343 9.28991 16.0868C9.21971 16.1392 9.13779 16.1738 9.05123 16.1876C8.96467 16.2013 8.87606 16.1938 8.79307 16.1656C8.71008 16.1374 8.63519 16.0895 8.57486 16.0259L5.38706 12.6608C5.3019 12.571 5.18847 12.5132 5.06576 12.497L0.469463 11.8958C0.382624 11.8844 0.299871 11.852 0.228341 11.8014C0.156812 11.7509 0.0986529 11.6837 0.0588803 11.6056C0.0191078 11.5276 -0.00108452 11.441 0.000044902 11.3535C0.00117433 11.2659 0.0235916 11.1799 0.0653633 11.1029L2.28116 7.0313C2.34007 6.92241 2.35977 6.79659 2.33696 6.6749L1.48826 2.1182C1.47215 2.03195 1.47729 1.94308 1.50325 1.85926C1.52921 1.77545 1.5752 1.69922 1.63724 1.63718C1.69928 1.57514 1.77551 1.52915 1.85932 1.50319C1.94314 1.47723 2.03201 1.47209 2.11826 1.4882L6.67496 2.3369C6.79665 2.35971 6.92247 2.34001 7.03136 2.2811L11.103 0.0653037C11.18 0.0235207 11.2661 0.00112163 11.3537 0.000041045C11.4414 -0.00103954 11.528 0.0192309 11.606 0.0591016C11.6841 0.0989722 11.7513 0.157245 11.8018 0.228886C11.8523 0.300528 11.8846 0.383386 11.8959 0.470304L12.4971 5.0657C12.5132 5.18841 12.5711 5.30184 12.6609 5.387L16.026 8.5748C16.0895 8.63513 16.1375 8.71002 16.1657 8.79301C16.1938 8.876 16.2014 8.96461 16.1876 9.05117C16.1739 9.13773 16.1393 9.21965 16.0868 9.28985C16.0344 9.36005 15.9656 9.41642 15.8865 9.4541L11.7015 11.4458C11.5894 11.4991 11.4992 11.5894 11.4459 11.7014ZM12.1632 13.4357L13.4358 12.1631L17.2545 15.9809L15.981 17.2544L12.1632 13.4357Z\" fill=\"#F96F4B\"><\/path><\/svg><\/span><\/p>\n\n\n\n<span class=\"gb-text cr-label-md gb-text-25cb5e23\">Key Takeaways<\/span>\n<\/div>\n\n\n\n<div class=\"cr-divider gb-element-a45cb2be\"><\/div>\n\n\n\n<div class=\"cr-bullet-row gb-element-8587908d\">\n<div class=\"cr-bullet-icon gb-element-12c5c71e\">\n<span class=\"cr-icon-18 gb-text-0bf494fd\"><span class=\"gb-shape\"><svg width=\"18\" height=\"18\" viewBox=\"0 0 18 18\" fill=\"none\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><circle cx=\"9\" cy=\"9\" r=\"5.4\" fill=\"#F96F4B\"><\/circle><circle cx=\"9\" cy=\"9\" r=\"4.4\" stroke=\"#FEE3D6\" stroke-width=\"2\"><\/circle><\/svg><\/span><\/span>\n<\/div>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-a1e2ed85\">llms.txt is a proposed Markdown index file at a site&#8217;s root that gives AI tools a curated map of the site&#8217;s most important content.<\/p>\n<\/div>\n\n\n\n<div class=\"cr-bullet-row gb-element-4372e86f\">\n<div class=\"cr-bullet-icon gb-element-bab2c330\">\n<span class=\"cr-icon-18 gb-text-40d8e065\"><span class=\"gb-shape\"><svg width=\"18\" height=\"18\" viewBox=\"0 0 18 18\" fill=\"none\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><circle cx=\"9\" cy=\"9\" r=\"5.4\" fill=\"#F96F4B\"><\/circle><circle cx=\"9\" cy=\"9\" r=\"4.4\" stroke=\"#FEE3D6\" stroke-width=\"2\"><\/circle><\/svg><\/span><\/span>\n<\/div>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-73486a3a\">The format is a proposal, not a standard, and differs from robots.txt, sitemap.xml and llms-full.txt, which inlines the entire documentation in a larger file.<\/p>\n<\/div>\n\n\n\n<div class=\"cr-bullet-row gb-element-527cd415\">\n<div class=\"cr-bullet-icon gb-element-71675ee2\">\n<span class=\"cr-icon-18 gb-text-8336e323\"><span class=\"gb-shape\"><svg width=\"18\" height=\"18\" viewBox=\"0 0 18 18\" fill=\"none\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><circle cx=\"9\" cy=\"9\" r=\"5.4\" fill=\"#F96F4B\"><\/circle><circle cx=\"9\" cy=\"9\" r=\"4.4\" stroke=\"#FEE3D6\" stroke-width=\"2\"><\/circle><\/svg><\/span><\/span>\n<\/div>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-07efca7e\">Google has never encouraged the use of llms.txt and Ahrefs data shows that 97% of published files got zero fetches in May 2026.<\/p>\n<\/div>\n\n\n\n<div class=\"cr-bullet-row gb-element-365ca264\">\n<div class=\"cr-bullet-icon gb-element-12494311\">\n<span class=\"cr-icon-18 gb-text-16fddf93\"><span class=\"gb-shape\"><svg width=\"18\" height=\"18\" viewBox=\"0 0 18 18\" fill=\"none\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><circle cx=\"9\" cy=\"9\" r=\"5.4\" fill=\"#F96F4B\"><\/circle><circle cx=\"9\" cy=\"9\" r=\"4.4\" stroke=\"#FEE3D6\" stroke-width=\"2\"><\/circle><\/svg><\/span><\/span>\n<\/div>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-296e7f6b\">As of 2026, llms.txt is therefore useless for most marketing purposes, with the developer docs and coding agents niche being the exception. Creating an llms.txt file is not that hard: docs-heavy sites can do it in about 20 minutes at near-zero cost.<\/p>\n<\/div>\n\n\n\n<div class=\"cr-bullet-row gb-element-57772d29\">\n<div class=\"cr-bullet-icon gb-element-7d813b3d\">\n<span class=\"cr-icon-18 gb-text-7b593198\"><span class=\"gb-shape\"><svg width=\"18\" height=\"18\" viewBox=\"0 0 18 18\" fill=\"none\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><circle cx=\"9\" cy=\"9\" r=\"5.4\" fill=\"#F96F4B\"><\/circle><circle cx=\"9\" cy=\"9\" r=\"4.4\" stroke=\"#FEE3D6\" stroke-width=\"2\"><\/circle><\/svg><\/span><\/span>\n<\/div>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-a2ac326c\">The definitive three-step test: (1) check server logs for \/llms.txt requests; (2) create the file if you find requests; (3) ignore if you don&#8217;t.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-dbc42193\">\n<p class=\"gb-text cr-p-md gb-text-893ea201\">llms.txt is a proposed Markdown file that sits at a website&#8217;s root path (yourdomain.com\/llms.txt) and gives AI systems a short, curated index of its most important pages. It&#8217;s not a rulebook for crawlers, but rather a reading list for language models.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-fa1e91f0\">But how big is llms.txt? Well, there&#8217;s a lot controversy around its importance because, even though the SEO industry pitched it as a shortcut for AI visibility, an Ahrefs llms.txt study from June 2026 shows <a href=\"https:\/\/ahrefs.com\/blog\/llmstxt-study\/\" target=\"_blank\" rel=\"noopener\">97% of llms.txt files never get read<\/a>.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-29b328ae\">This guide simplifies llms.txt by covering what the file is, what it looks like, who uses it and whether it deserves 20 minutes of your time.<\/p>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-1fdc9968\">\n<h2 id=\"what-is-llmstxt\" class=\"gb-text cr-h5 gb-text-84507411\">What is llms.txt?<\/h2>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-d28e4b77\">The proposed standard llms.txt is a single Markdown index file at a site&#8217;s root that summarizes the site&#8217;s most important content and links out to it. Its main purpose is to help AI systems orient themselves without crawling every page. The <a href=\"https:\/\/llmstxt.org\/\" target=\"_blank\" rel=\"noopener\">llms.txt spec<\/a> frames it as inference-time assistance, not crawl-time indexing.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-987d3a0a\">The problem the file targets is real. Language models work with limited context windows, so they can&#8217;t ingest an entire website in one go. Raw HTML doesn&#8217;t help either, since navigation, scripts and boilerplate bury the actual content. In theory, a hand-picked Markdown index sidesteps both problems at once.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-9207af7a\">The format was <a href=\"https:\/\/www.linkedin.com\/posts\/ethanls_the-myth-of-llmstxt-jeremy-howard-of-activity-7404973352085344256-8Qwt\" target=\"_blank\" rel=\"noopener\">first proposed by Jeremy Howard<\/a>, the Answer.AI co-founder. His pitch was practical, not promotional: the idea was to give AI systems a clean map of what matters on a site and skip the noise. Ranking promises were no part of it.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-8aaa0d01\">Nevertheless, llms.txt is a proposal, not a ratified standard. No standards body has adopted it, nothing about it is official and no major AI platform has committed to reading it. That&#8217;s something we will have to keep in mind for the rest of the article.<\/p>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-5f5b2840\">\n<h2 id=\"what-does-an-llmstxt-file-look-like\" class=\"gb-text cr-h5 gb-text-0b548d0d\">What does an llms.txt file look like?<\/h2>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-d3da959f\">The format is deliberately minimal Markdown. The spec only has one hard requirement: an H1 with the site or project name. Everything else is optional, from the blockquote summary under the title to the H2-grouped lists of links with short descriptions.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-3fdad446\">Here&#8217;s a realistic example for a fictional SaaS docs site:<\/p>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-0bf99043\">\n<h2 id=\"acmemetrics\" class=\"gb-text cr-h5 gb-text-760acb02\">AcmeMetrics<\/h2>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-466346e3\">\n<p class=\"gb-text cr-p-md gb-text-180001fd\">AcmeMetrics exposes a REST API and a JavaScript SDK. Most integration questions are answered in the API reference.<\/p>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-01a1ff0c\">\n<div class=\"cr-block-6 gb-element-5d3f0570\">\n<h2 id=\"docs\" class=\"gb-text cr-h5 gb-text-dfd53aae\">Docs<\/h2>\n<\/div>\n\n\n\n<ul class=\"cr-ul gb-element-b916a4d7\">\n<li class=\"gb-text gb-text-b0e2ee36\"><a href=\"https:\/\/docs.acmemetrics.com\/quickstart.md\" target=\"_blank\" rel=\"noopener\">Quickstart<\/a>: install, authenticate and send your first event<\/li>\n\n\n\n<li class=\"gb-text gb-text-56f5fddd\"><a href=\"https:\/\/docs.acmemetrics.com\/api.md\" target=\"_blank\" rel=\"noopener\">API reference<\/a>: every endpoint with request and response examples<\/li>\n<\/ul>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-bd16c768\">\n<div class=\"cr-block-6 gb-element-31ce0542\">\n<h2 id=\"optional\" class=\"gb-text cr-h5 gb-text-b8bfd7ca\">Optional<\/h2>\n<\/div>\n\n\n\n<ul class=\"cr-ul gb-element-2960e6ed\">\n<li class=\"gb-text gb-text-128c7ee5\"><a href=\"https:\/\/docs.acmemetrics.com\/changelog.md\" target=\"_blank\" rel=\"noopener\">Changelog<\/a>: release notes by month<\/li>\n\n\n\n<li class=\"gb-text gb-text-c83fa467\"><a href=\"https:\/\/forum.acmemetrics.com\" target=\"_blank\" rel=\"noopener\">Community forum<\/a>: user discussions and workarounds<\/li>\n<\/ul>\n\n\n\n<ol class=\"cr-ol gb-element-9ab05f81\">\n<li class=\"gb-text gb-text-da760006\">The blockquote gives an AI a one-line summary before it reads anything else<\/li>\n\n\n\n<li class=\"gb-text gb-text-e5cbff6f\">Each link carries a short description, so a model can decide what to fetch without fetching it<\/li>\n\n\n\n<li class=\"gb-text gb-text-2c915d85\">The &#8220;Optional&#8221; section flags content an AI can skip when it&#8217;s short on context<\/li>\n<\/ol>\n\n\n\n<div class=\"cr-block-6 gb-element-b5a3e807\">\n<p class=\"gb-text cr-p-md gb-text-8640f3b1\">Creating an llms.txt file takes minutes, not days, and you should hold on to that thought. The low cost matters later on, when the question becomes whether the file earns even that.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-82e488d4\">\n<div class=\"cr-block-6 gb-element-f3a2da9c\">\n<h2 id=\"llmstxt-vs-robotstxt-and-sitemapxml\" class=\"gb-text cr-h5 gb-text-e4762ef9\">llms.txt vs robots.txt and sitemap.xml<\/h2>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-4765ee4a\">Despite the filename, llms.txt is not an access-control file. It blocks and controls nothing. It&#8217;s an informational index, closer in spirit to a sitemap than to robots.txt, except it&#8217;s designed for machine reading instead of exhaustive listing.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-39f6c371\">Confusing? This is the cleanest way to hold the three apart:<\/p>\n<\/div>\n\n\n\n<ul class=\"cr-ul gb-element-11a47062\">\n<li class=\"gb-text gb-text-710f61ef\">robots.txt is permissions<\/li>\n\n\n\n<li class=\"gb-text gb-text-ade40d48\">sitemap.xml is inventory<\/li>\n\n\n\n<li class=\"gb-text gb-text-19ed7d90\">llms.txt is curation<\/li>\n<\/ul>\n\n\n\n<div class=\"cr-block-6 gb-element-d7c2bdb9\">\n<p class=\"gb-text cr-p-md gb-text-bad27b8f\">The table further illustrates the differences:<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-d9ef5ae1\">\n<div class=\"cr-tblwrap gb-element-1b376897\">\n<div class=\"cr-table2 cr-avc-4 gb-element-650c5431\">\n<div class=\"cr-tr2 cr-tr2-head gb-element-6600d82d\">\n<span class=\"gb-text cr-th2 gb-text-0d4fa6f4\"><\/span>\n\n\n\n<span class=\"gb-text cr-th2 gb-text-eac18ead\">llms.txt<\/span>\n\n\n\n<span class=\"gb-text cr-th2 gb-text-caf0be22\">robots.txt<\/span>\n\n\n\n<span class=\"gb-text cr-th2 gb-text-4c404d42\">sitemap.xml<\/span>\n<\/div>\n\n\n\n<div class=\"cr-tr2 gb-element-97b49cde\">\n<span class=\"gb-text cr-td2 gb-text-d6b0f0b4\"><span class=\"cr-strong\">Purpose<\/span><\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-4e883566\">Curated index of what matters, with context<\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-178ee7ca\">Rules for what bots may crawl<\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-853fa2ab\">Complete list of URLs<\/span>\n<\/div>\n\n\n\n<div class=\"cr-tr2 cr-tr2-alt gb-element-d4a5018d\">\n<span class=\"gb-text cr-td2 gb-text-44c96d60\"><span class=\"cr-strong\">Audience<\/span><\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-444f60ef\">LLMs and AI agents<\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-d33dd5b3\">Search engine crawlers<\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-c705d6e1\">Search engine crawlers<\/span>\n<\/div>\n\n\n\n<div class=\"cr-tr2 gb-element-6992d1f6\">\n<span class=\"gb-text cr-td2 gb-text-7b034052\"><span class=\"cr-strong\">Controls access?<\/span><\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-0f747a38\">No<\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-77910c5b\">Yes<\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-35768ea4\">No<\/span>\n<\/div>\n\n\n\n<div class=\"cr-tr2 cr-tr2-alt gb-element-1dea4701\">\n<span class=\"gb-text cr-td2 gb-text-13b24639\"><span class=\"cr-strong\">Format<\/span><\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-03a919f9\">Markdown<\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-db55a037\">Plain text directives<\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-573ba99f\">XML<\/span>\n<\/div>\n\n\n\n<div class=\"cr-tr2 gb-element-00415795\">\n<span class=\"gb-text cr-td2 gb-text-2f6fd865\"><span class=\"cr-strong\">Status<\/span><\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-e95201b6\">Proposal (2024)<\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-6d99b4f6\">De facto standard since 1994<\/span>\n\n\n\n<span class=\"gb-text cr-td2 gb-text-c24b248f\">Adopted standard<\/span>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-e3c66c94\">\n<p class=\"gb-text cr-p-md gb-text-0df1e511\">llms.txt doesn&#8217;t replace robots.txt and sitemap.xml, coexisting with both files. Adding an llms.txt file doesn&#8217;t affect your existing crawl setup.<\/p>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-75fe1ee5\">\n<h2 id=\"llmstxt-vs-llmsfulltxt-vs-md-files\" class=\"gb-text cr-h5 gb-text-5cb0f2ba\">llms.txt vs llms-full.txt vs .md files<\/h2>\n<\/div>\n\n\n\n<img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"451\" class=\"gb-media-eb1ea73a gb-media-eb1ea73a\" src=\"https:\/\/crowdreply.io\/blog\/wp-content\/uploads\/2026\/07\/llms-txt-versus-llms-txt-full-quick-comparison.png\" alt=\"image comparing llms.txt and llms full side by side\" style=\"width:100%;height:auto\" srcset=\"https:\/\/crowdreply.io\/blog\/wp-content\/uploads\/2026\/07\/llms-txt-versus-llms-txt-full-quick-comparison.png 1024w, https:\/\/crowdreply.io\/blog\/wp-content\/uploads\/2026\/07\/llms-txt-versus-llms-txt-full-quick-comparison-300x132.png 300w, https:\/\/crowdreply.io\/blog\/wp-content\/uploads\/2026\/07\/llms-txt-versus-llms-txt-full-quick-comparison-768x338.png 768w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/>\n\n\n\n<div class=\"cr-block-12 gb-element-a8552ec2\">\n<div class=\"cr-block-6 gb-element-9b4e1ce7\">\n<p class=\"gb-text cr-p-md gb-text-399078c8\">Readers get these files wrong all the time, so here&#8217;s a straightforward take on each of the three:<\/p>\n<\/div>\n\n\n\n<ol class=\"cr-ol gb-element-3b9940b1\">\n<li class=\"gb-text gb-text-af90e59e\"><span class=\"cr-strong\">llms.txt<\/span>: it&#8217;s the short index, comprised of a list of links with descriptions that should be small enough to read in one pass.<\/li>\n\n\n\n<li class=\"gb-text gb-text-fd766a47\"><span class=\"cr-strong\">llms-full.txt:<\/span> meant to inline the full text of the documentation into one large file, allowing tools to load everything at once instead of following links.<\/li>\n\n\n\n<li class=\"gb-text gb-text-0c50e62c\"><span class=\"cr-strong\">.md files:<\/span> serve a clean Markdown copy of any page (to check the clean copy, you just have to add .md to the site&#8217;s URL).<\/li>\n<\/ol>\n\n\n\n<div class=\"cr-block-6 gb-element-2cb44926\">\n<p class=\"gb-text cr-p-md gb-text-1bdebf26\">For a better understanding of the differences between llms.txt and llms-full.txt, you just have to open your favorite website, add either llms.txt or llms-full.txt to the URL and click enter.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-992bcf31\">Anthropic is a useful example. The <a href=\"https:\/\/platform.claude.com\/llms.txt\" target=\"_blank\" rel=\"noopener\">llms.txt version<\/a> indexes everything into a short collection of essential links, whereas the <a href=\"https:\/\/platform.claude.com\/llms-full.txt\" target=\"_blank\" rel=\"noopener\">llms-full.txt version<\/a> is extremely long and detailed in comparison.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-5e161a42\">Which one you&#8217;d actually maintain is mostly decided for you because docs platforms generate these files automatically. That convenience leads straight into the adoption question.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-4d69991d\">\n<h2 id=\"who-actually-uses-llmstxt\" class=\"gb-text cr-h5 gb-text-a56fd410\">Who actually uses llms.txt?<\/h2>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-e661076e\">Real adoption exists. You can check it from a browser tab right now: Anthropic, Stripe, Cloudflare and Perplexity all serve live llms.txt files on their developer-docs domains. The pattern is clear: we&#8217;re looking at technical documentation, not marketing sites.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-2bdc22c8\">A big share of that adoption arrived automatically. Mintlify, for example, started <a href=\"https:\/\/www.mintlify.com\/docs\/ai\/llmstxt\" target=\"_blank\" rel=\"noopener\">generating \/llms.txt and \/llms-full.txt for every docs site it hosts<\/a>, which gave thousands of sites the file at once. This is problematic because the raw adoption numbers (i.e., how many sites serve live llms.txt files) don&#8217;t necessarily tell us whether teams have intentionally decided to adopt the format or if it was automatically incorporated.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-36aaaa67\">There&#8217;s one more catch: publishing an llms.tx file and having it read are different things. No major AI platform has yet committed to the format, and that begs the question:<\/p>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-6de8f308\">\n<h2 id=\"does-llmstxt-actually-work\" class=\"gb-text cr-h5 gb-text-04a15e66\">Does llms.txt actually work?<\/h2>\n<\/div>\n\n\n\n<img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"558\" class=\"gb-media-1b69a0a6 gb-media-1b69a0a6\" src=\"https:\/\/crowdreply.io\/blog\/wp-content\/uploads\/2026\/07\/sites-with-a-valid-llms-txt-file.png\" alt=\"graphic displaying the number of sites with a valid llms.txt page in 2026\" style=\"width:100%;height:auto\" srcset=\"https:\/\/crowdreply.io\/blog\/wp-content\/uploads\/2026\/07\/sites-with-a-valid-llms-txt-file.png 1024w, https:\/\/crowdreply.io\/blog\/wp-content\/uploads\/2026\/07\/sites-with-a-valid-llms-txt-file-300x163.png 300w, https:\/\/crowdreply.io\/blog\/wp-content\/uploads\/2026\/07\/sites-with-a-valid-llms-txt-file-768x419.png 768w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/>\n\n\n\n<div class=\"cr-block-12 gb-element-f3d02087\">\n<p class=\"gb-text cr-p-md gb-text-f1267700\">On the evidence available in mid-2026, llms.txt does nothing for search or AI visibility on the general web. This conclusion is backed by two major sources: the 2026 llms.txt study published by Ahrefs and Google.<\/p>\n\n\n\n<h3 id=\"1-what-the-ahrefs-llmstxt-study-shows\" class=\"gb-text cr-h6 gb-text-b95799cb\">1 &#8211; What the Ahrefs llms.txt study shows<\/h3>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-4d8d2f68\">Remember that Ahrefs study we&#8217;ve mentioned above? This is its boldest, most enlightening take:<\/p>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-3c14c06b\">\n<p class=\"gb-text cr-p-md gb-text-6ee36864\">The small slice that did get traffic doesn&#8217;t rescue the story either, since only 19.5% of those fetches came from AI tools. One caveat cuts both ways: this measures fetch traffic to the file itself, not AI citation outcomes. However, what&#8217;s the point of llms.txt files if nobody reads them?<\/p>\n\n\n\n<h3 id=\"2-what-google-says\" class=\"gb-text cr-h6 gb-text-971015f9\">2 &#8211; What Google says<\/h3>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-e919d476\">Google&#8217;s initial position was loud and clear, as reported by Search Engine Land in July 2025: llms.txt was <a href=\"https:\/\/searchengineland.com\/google-says-normal-seo-works-for-ranking-in-ai-overviews-and-llms-txt-wont-be-used-459422\" target=\"_blank\" rel=\"noopener\">not to be used for SEO and the AI Overviews<\/a>. That position, however, has recently changed. In mid-2026, Google stated that <a href=\"https:\/\/www.searchenginejournal.com\/googles-says-its-fine-to-use-llms-txt-for-ai-seo\/579608\/\" target=\"_blank\" rel=\"noopener\">it&#8217;s fine to use llms.txt for AI SEO<\/a> despite being previously dismissive of the format, to the point of discouraging its use.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-450aebb1\">Google&#8217;s change of heart is encouraging for llms.txt adopters, but it doesn&#8217;t change the fundamental fact that the vast majority of files aren&#8217;t read. This helps to explain why Google&#8217;s John Mueller <a href=\"https:\/\/www.searchenginejournal.com\/googles-mueller-says-llms-txt-cant-help-llms-differentiate-sites\/579304\/\" target=\"_blank\" rel=\"noopener\">compared llms.txt files to the old keywords meta tag<\/a>. At least for now, both are existing signals that search systems simply don&#8217;t consume.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-8452fe9f\">Nevertheless, the importance of the llms.txt format is still open for debate&#8230;<\/p>\n\n\n\n<h3 id=\"the-countercase-docs-and-coding-agents\" class=\"gb-text cr-h6 gb-text-3932b93a\">The counter-case: docs and coding agents<\/h3>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-d50a2c5b\">The data isn&#8217;t uniformly negative. Within the small share of files that actually got fetched, GPTBot led and Claude-Code came second, both ahead of all the search and assistant bots. That&#8217;s coding tools reading developer docs, not search engines evaluating marketing sites.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-9d1c9157\">Mueller&#8217;s own framing points in the same direction. He called llms.txt a &#8220;temporary crutch&#8221; that might save AI coding tools some tokens while they parse developer docs. Some individual site owners report heavier traffic, like one operator whose logs showed OpenAI hitting his llms.txt every 15 minutes. That&#8217;s one site&#8217;s logs, not a trend.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-529f7f2d\">The honest read? llms.txt files are not a ranking leveler for <em>everyone<\/em>, but they can be a real niche <em>for docs and agents<\/em>.<\/p>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-343d5371\">\n<div class=\"cr-block-6 gb-element-f2c46be3\">\n<h2 id=\"common-misconceptions-about-llmstxt\" class=\"gb-text cr-h5 gb-text-caff6c99\">Common misconceptions about llms.txt<\/h2>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-57634a05\">If you&#8217;re still a bit confused, there&#8217;s a good chance you&#8217;re being misguided by one of these four llms.txt misconceptions:<\/p>\n<\/div>\n\n\n\n<ol class=\"cr-ol gb-element-9a0cebf6\">\n<li class=\"gb-text gb-text-aacd6838\"><span class=\"cr-strong\">&#8220;llms.txt boosts your rankings or AI visibility.&#8221;<\/span> The spec never claimed this. Not once. This myth is a sole product of the SEO industry.<\/li>\n\n\n\n<li class=\"gb-text gb-text-ea6129f7\"><span class=\"cr-strong\">&#8220;Google told SEOs to create it.&#8221;<\/span> Not true. Google&#8217;s initial position was actually the opposite, and despite a recent change of heart, the company never endorsed the format.<\/li>\n\n\n\n<li class=\"gb-text gb-text-a9d8d9d7\"><span class=\"cr-strong\">&#8220;It controls AI crawlers like robots.txt.&#8221;<\/span> llms.txt files are an index, not a directive. Unlike robots.txt, they block nothing.<\/li>\n\n\n\n<li class=\"gb-text gb-text-6a671a0e\"><span class=\"cr-strong\">&#8220;99.14% of llms.txt files got zero requests.&#8221;<\/span> This is an exaggerated and unverified stat published in some sources. The official number is 97%, as reported by the Ahrefs study.<\/li>\n<\/ol>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-29693dc1\">\n<div class=\"cr-block-6 gb-element-67654682\">\n<h2 id=\"should-you-create-an-llmstxt-file\" class=\"gb-text cr-h5 gb-text-22a275e6\">Should you create an llms.txt file?<\/h2>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-7eaf76dd\">Yes, the importance of llms.txt files has been grossly overstated by the SEO industry, but that doesn&#8217;t mean the answer is always no. In sum:<\/p>\n<\/div>\n\n\n\n<ol class=\"cr-ol gb-element-369dafe8\">\n<li class=\"gb-text gb-text-8912a106\"><span class=\"cr-strong\">Creating an llms.txt file is worth it if you run developer docs or API reference content<\/span>. Coding agents already fetch these files, the cost is near zero and there&#8217;s no downside. It takes 20 minutes or less, so why not?<\/li>\n\n\n\n<li class=\"gb-text gb-text-7ada99fd\"><b>It&#8217;s not worth it if <\/b><span class=\"cr-strong\">you&#8217;re a general marketing site hoping for SEO or AI-visibility gains. <\/span>We wish answer engine optimization was this easy, but the evidence says the bots aren&#8217;t reading llms.txt files. In this case, even 20 minutes feels like a waste&#8230;<\/li>\n<\/ol>\n\n\n\n<div class=\"cr-block-6 gb-element-c669f46f\">\n<p class=\"gb-text cr-p-md gb-text-7eaf776d\">If you&#8217;re in the worth-it camp, here&#8217;s how easy it is to create an llms.txt file:<\/p>\n<\/div>\n\n\n\n<ol class=\"cr-ol gb-element-35f23e2f\">\n<li class=\"gb-text gb-text-2b77ecef\">Decide which pages an AI should read first (usually, your quickstart and reference docs);<\/li>\n\n\n\n<li class=\"gb-text gb-text-59c2016b\">Write the Markdown file: one H1, a summary blockquote and grouped link lists;<\/li>\n\n\n\n<li class=\"gb-text gb-text-8d4b4523\">Upload it to your site&#8217;s root so it resolves at yourdomain.com\/llms.txt.<\/li>\n<\/ol>\n\n\n\n<div class=\"cr-block-6 gb-element-8622f959\">\n<p class=\"gb-text cr-p-md gb-text-7d52270a\">An important detail to keep in mind: if your docs live on GitBook or Mintlify, you probably already have an llms.txt. These files can easily go unnoticed, so don&#8217;t forget to check before you build one by hand.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-a09ba3b2\">\n<h2 id=\"the-definitive-llmstxt-test\" class=\"gb-text cr-h5 gb-text-c0574201\">The definitive llms.txt test<\/h2>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-455365a2\">In conclusion, llms.txt is a real, simple, live proposal whose proven value is extremely narrow. As of mid-2026, it&#8217;s a useful low-cost index for docs sites and coding agents. If you don&#8217;t fit the bill, there&#8217;s no real reason to worry about the format.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-34950af2\">But hey, isn&#8217;t utterly ignoring llms.txt ill-advised? Well, there&#8217;s one easy test that settles the matter:<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-d44ae35c\">Before spending anything on llms.txt, check your server logs for \/llms.txt requests. If AI bots are already asking for the file, the 20-minute setup is worth it. If not, place your time and energy elsewhere.<\/p>\n\n\n\n<p class=\"gb-text cr-p-md gb-text-ee952aa3\">To learn more about how AI systems talk about you right now, you just have to <a href=\"https:\/\/crowdreply.io\/\">run your brand through CrowdReply<\/a> to see how the engines actually describe you.<\/p>\n<\/div>\n\n\n\n<div class=\"cr-block-12 gb-element-ad2c067d\">\n<div class=\"cr-block-6 gb-element-57604749\">\n<h2 id=\"frequently-asked-questions\" class=\"gb-text cr-h5 gb-text-e0e95007\">Frequently Asked Questions<\/h2>\n<\/div>\n\n\n\n<div class=\"gb-accordion cr-acc gb-element-8c3419d0\" data-transition=\"slide\">\n<div class=\"gb-accordion__item cr-acc-item gb-accordion__item-open gb-element-77cd0446\">\n<div role=\"button\" tabindex=\"0\" class=\"gb-accordion__toggle cr-acc-toggle gb-element-6e381571 gb-block-is-current\" id=\"gb-accordion-toggle-6e381571\">\n<span class=\"gb-text cr-acc-num gb-text-3d5eca43\">01<\/span>\n\n\n\n<span class=\"gb-text cr-acc-q gb-text-099b8f64\">Do AI crawlers actually read llms.txt?<\/span>\n\n\n\n<span class=\"gb-accordion__toggle-icon cr-acc-icon gb-element-bff2fc15\"><span class=\"gb-accordion__toggle-icon-open\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M1.646 4.646a.5.5 0 0 1 .708 0L8 10.293l5.646-5.647a.5.5 0 0 1 .708.708l-6 6a.5.5 0 0 1-.708 0l-6-6a.5.5 0 0 1 0-.708\"><\/path><\/svg><\/span><span class=\"gb-accordion__toggle-icon-close\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M7.646 4.646a.5.5 0 0 1 .708 0l6 6a.5.5 0 0 1-.708.708L8 5.707l-5.646 5.647a.5.5 0 0 1-.708-.708z\"><\/path><\/svg><\/span><\/span>\n<\/div>\n\n\n\n<div class=\"gb-accordion__content cr-acc-content gb-element-9bed4dcf\" id=\"gb-accordion-content-9bed4dcf\">\n<p class=\"gb-text cr-acc-a gb-text-d5186135\">Mostly, they don&#8217;t. 97% of published llms.txt files got zero requests in mid-2026 and Google initially stated its systems don&#8217;t use the file at all. The exception is developer documentation, where coding-agent bots like GPTBot and Claude-Code do fetch the files.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"gb-accordion__item cr-acc-item gb-element-25b1dbe4\">\n<div role=\"button\" tabindex=\"0\" class=\"gb-accordion__toggle cr-acc-toggle gb-element-42730762\" id=\"gb-accordion-toggle-42730762\">\n<span class=\"gb-text cr-acc-num gb-text-a5837f75\">02<\/span>\n\n\n\n<span class=\"gb-text cr-acc-q gb-text-f5c4458a\">Does llms.txt help SEO?<\/span>\n\n\n\n<span class=\"gb-accordion__toggle-icon cr-acc-icon gb-element-2430a575\"><span class=\"gb-accordion__toggle-icon-open\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M1.646 4.646a.5.5 0 0 1 .708 0L8 10.293l5.646-5.647a.5.5 0 0 1 .708.708l-6 6a.5.5 0 0 1-.708 0l-6-6a.5.5 0 0 1 0-.708\"><\/path><\/svg><\/span><span class=\"gb-accordion__toggle-icon-close\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M7.646 4.646a.5.5 0 0 1 .708 0l6 6a.5.5 0 0 1-.708.708L8 5.707l-5.646 5.647a.5.5 0 0 1-.708-.708z\"><\/path><\/svg><\/span><\/span>\n<\/div>\n\n\n\n<div class=\"gb-accordion__content cr-acc-content gb-element-0ff0a9b5\" id=\"gb-accordion-content-0ff0a9b5\">\n<p class=\"gb-text cr-acc-a gb-text-423be138\">No. Google has said on the record that it does not use llms.txt and that appearing in AI Overviews takes normal SEO, nothing extra. John Mueller compared it to the old keywords meta tag, a signal search systems simply don&#8217;t consume.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"gb-accordion__item cr-acc-item gb-element-3afe99ae\">\n<div role=\"button\" tabindex=\"0\" class=\"gb-accordion__toggle cr-acc-toggle gb-element-fb9ba237\" id=\"gb-accordion-toggle-fb9ba237\">\n<span class=\"gb-text cr-acc-num gb-text-ed28ad75\">03<\/span>\n\n\n\n<span class=\"gb-text cr-acc-q gb-text-6d498720\">Is there an official llms.txt standard?<\/span>\n\n\n\n<span class=\"gb-accordion__toggle-icon cr-acc-icon gb-element-18cb917a\"><span class=\"gb-accordion__toggle-icon-open\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M1.646 4.646a.5.5 0 0 1 .708 0L8 10.293l5.646-5.647a.5.5 0 0 1 .708.708l-6 6a.5.5 0 0 1-.708 0l-6-6a.5.5 0 0 1 0-.708\"><\/path><\/svg><\/span><span class=\"gb-accordion__toggle-icon-close\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M7.646 4.646a.5.5 0 0 1 .708 0l6 6a.5.5 0 0 1-.708.708L8 5.707l-5.646 5.647a.5.5 0 0 1-.708-.708z\"><\/path><\/svg><\/span><\/span>\n<\/div>\n\n\n\n<div class=\"gb-accordion__content cr-acc-content gb-element-ddea4724\" id=\"gb-accordion-content-ddea4724\">\n<p class=\"gb-text cr-acc-a gb-text-ce8140a6\">No. llms.txt is a proposal, not a ratified standard. No standards body has adopted it and no major AI platform has committed to reading it. For now, it remains community-driven.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"gb-accordion__item cr-acc-item gb-element-7bfc6a76\">\n<div role=\"button\" tabindex=\"0\" class=\"gb-accordion__toggle cr-acc-toggle gb-element-cfbbc42b\" id=\"gb-accordion-toggle-cfbbc42b\">\n<span class=\"gb-text cr-acc-num gb-text-932db624\">04<\/span>\n\n\n\n<span class=\"gb-text cr-acc-q gb-text-bd358378\">Should I create an llms.txt file?<\/span>\n\n\n\n<span class=\"gb-accordion__toggle-icon cr-acc-icon gb-element-9950eecf\"><span class=\"gb-accordion__toggle-icon-open\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M1.646 4.646a.5.5 0 0 1 .708 0L8 10.293l5.646-5.647a.5.5 0 0 1 .708.708l-6 6a.5.5 0 0 1-.708 0l-6-6a.5.5 0 0 1 0-.708\"><\/path><\/svg><\/span><span class=\"gb-accordion__toggle-icon-close\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M7.646 4.646a.5.5 0 0 1 .708 0l6 6a.5.5 0 0 1-.708.708L8 5.707l-5.646 5.647a.5.5 0 0 1-.708-.708z\"><\/path><\/svg><\/span><\/span>\n<\/div>\n\n\n\n<div class=\"gb-accordion__content cr-acc-content gb-element-85fc125c\" id=\"gb-accordion-content-85fc125c\">\n<p class=\"gb-text cr-acc-a gb-text-2b1e5614\">You should do it for docs-heavy or API-reference sites, where the cost is near zero and coding agents already fetch the files. It&#8217;s not worth it for general marketing sites expecting visibility gains.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"gb-accordion__item cr-acc-item gb-element-27cd490c\">\n<div role=\"button\" tabindex=\"0\" class=\"gb-accordion__toggle cr-acc-toggle gb-element-148f4ee1\" id=\"gb-accordion-toggle-148f4ee1\">\n<span class=\"gb-text cr-acc-num gb-text-297a9fc2\">05<\/span>\n\n\n\n<span class=\"gb-text cr-acc-q gb-text-2942e59b\">What is llms-full.txt?<\/span>\n\n\n\n<span class=\"gb-accordion__toggle-icon cr-acc-icon gb-element-8b55a7a2\"><span class=\"gb-accordion__toggle-icon-open\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M1.646 4.646a.5.5 0 0 1 .708 0L8 10.293l5.646-5.647a.5.5 0 0 1 .708.708l-6 6a.5.5 0 0 1-.708 0l-6-6a.5.5 0 0 1 0-.708\"><\/path><\/svg><\/span><span class=\"gb-accordion__toggle-icon-close\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M7.646 4.646a.5.5 0 0 1 .708 0l6 6a.5.5 0 0 1-.708.708L8 5.707l-5.646 5.647a.5.5 0 0 1-.708-.708z\"><\/path><\/svg><\/span><\/span>\n<\/div>\n\n\n\n<div class=\"gb-accordion__content cr-acc-content gb-element-335ce56e\" id=\"gb-accordion-content-335ce56e\">\n<p class=\"gb-text cr-acc-a gb-text-1ad2fbcd\">A companion file that inlines the full text of a site&#8217;s documentation into one large file, where llms.txt itself is only a short index of links.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"gb-accordion__item cr-acc-item gb-element-e1071080\">\n<div role=\"button\" tabindex=\"0\" class=\"gb-accordion__toggle cr-acc-toggle gb-element-44782441\" id=\"gb-accordion-toggle-44782441\">\n<span class=\"gb-text cr-acc-num gb-text-15534c59\">06<\/span>\n\n\n\n<span class=\"gb-text cr-acc-q gb-text-00552ca6\">Where should llms.txt live?<\/span>\n\n\n\n<span class=\"gb-accordion__toggle-icon cr-acc-icon gb-element-0a129f7a\"><span class=\"gb-accordion__toggle-icon-open\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M1.646 4.646a.5.5 0 0 1 .708 0L8 10.293l5.646-5.647a.5.5 0 0 1 .708.708l-6 6a.5.5 0 0 1-.708 0l-6-6a.5.5 0 0 1 0-.708\"><\/path><\/svg><\/span><span class=\"gb-accordion__toggle-icon-close\"><svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 16 16\" fill=\"currentColor\"><path fill-rule=\"evenodd\" d=\"M7.646 4.646a.5.5 0 0 1 .708 0l6 6a.5.5 0 0 1-.708.708L8 5.707l-5.646 5.647a.5.5 0 0 1-.708-.708z\"><\/path><\/svg><\/span><\/span>\n<\/div>\n\n\n\n<div class=\"gb-accordion__content cr-acc-content gb-element-90807c26\" id=\"gb-accordion-content-90807c26\">\n<p class=\"gb-text cr-acc-a gb-text-92f085a5\">llms.txt should live at the site&#8217;s root path, as in yourdomain.com\/llms.txt (the same convention robots.txt uses). Subdomain roots work the same way.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>What is llms.txt? A proposed Markdown index file that gives AI tools a map of your site. See a real example, who uses it and whether bots actually read it.<\/p>\n","protected":false},"author":9,"featured_media":2226,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_cr_post_editor_id":5,"footnotes":""},"categories":[8],"tags":[],"class_list":["post-2133","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-search"],"_links":{"self":[{"href":"https:\/\/crowdreply.io\/blog\/wp-json\/wp\/v2\/posts\/2133","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/crowdreply.io\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/crowdreply.io\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/crowdreply.io\/blog\/wp-json\/wp\/v2\/users\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/crowdreply.io\/blog\/wp-json\/wp\/v2\/comments?post=2133"}],"version-history":[{"count":13,"href":"https:\/\/crowdreply.io\/blog\/wp-json\/wp\/v2\/posts\/2133\/revisions"}],"predecessor-version":[{"id":3524,"href":"https:\/\/crowdreply.io\/blog\/wp-json\/wp\/v2\/posts\/2133\/revisions\/3524"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/crowdreply.io\/blog\/wp-json\/wp\/v2\/media\/2226"}],"wp:attachment":[{"href":"https:\/\/crowdreply.io\/blog\/wp-json\/wp\/v2\/media?parent=2133"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/crowdreply.io\/blog\/wp-json\/wp\/v2\/categories?post=2133"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/crowdreply.io\/blog\/wp-json\/wp\/v2\/tags?post=2133"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}