--- title: "What is llms.txt | Google Search ignores it | Len P. van der Hof" description: llms.txt is a voluntary Markdown map for agents and retrieval clients that choose to read it. It does not control crawling, replace a sitemap, or move Google… image: "https://lenvanderhof.com/media/generated/blog-hero-llms-txt-v1.1d06121fea07.wide.webp" --- [SEO, GEO and AEO](https://lenvanderhof.com/en/blog/category/seo-geo-aeo/) Research guide # What is llms.txt? A manifesto, not a ranking switch A voluntary map guides the client that opens it. It has no power over one that never asks. Len P. van der HofPublished 22 September 20264 min read The notice helps only the reader who chooses to stop. Direct answer llms.txt is a proposed Markdown file, named llms.txt, published at a site's root or at any path within it. It gives agents and retrieval clients a short description of the site or section plus curated links to more detailed, preferably machine-readable pages. Reading it is voluntary. The only required element is an H1. It is not robots.txt, not an access control, and not a replacement for a sitemap. Google's guide to generative AI features in Search, last updated 2026-07-10 and re-read 2026-09-04, says Google Search does not use such files and that creating one neither helps nor harms visibility or rankings, including in generative features such as AI Overviews and AI Mode. ## Key takeaways - llms.txt is a proposal, now at version 2, for a concise Markdown guide to a site or section. Clients must choose to read it. - Google Search ignores llms.txt. Publishing one neither helps nor harms visibility or rankings, generative features included. - robots.txt sets crawler permissions, a sitemap aids discovery, llms.txt offers optional guidance. None does another's job. - Publish the file only when you can name the intended reader and someone owns keeping every listed URL current. **llms.txt is a voluntary map for machines.** You publish a small Markdown file. An agent or retrieval client that chooses to read it gets a short description of your site and the links you selected. Nothing obliges any system to open it, and the file has no power over one that never does. The proposal, now at version 2, asks for a file named `llms.txt` at the site root or at any path within it, covering the pages under that path. The only required element is an H1 with the name of the site or project. Everything else is optional: a one-paragraph summary in a blockquote, short guidance, H2 lists of links with one-line descriptions, and an “Optional” section for secondary material. It was first published in September 2024 and revised in August 2026. It is a proposal, not a standard. It is not a well-known URI either; the authors deliberately stayed out of `/.well-known/`, because a well-known URI can only live at the origin root and this file is meant to cover a path. Google’s answer is unusually plain. Its guide to generative AI features in Search says Google Search does not use such files, and that creating one will neither help nor harm your site’s visibility or rankings in Google Search. That includes the generative features, AI Overviews and AI Mode among them. So “does llms.txt help Google?” has an answer: no, and it does not hurt either. Whether some other client finds the file useful is a separate question, and only your logs can answer it. ## llms.txt, robots.txt, and sitemap.xml The three files answer different questions: FileJobWhat it cannot promisellms.txtOffers optional context and a curated path through your content to clients that read itCrawl compliance, indexing, ranking, citation, or adoption by any clientrobots.txtStates crawler permissions by user-agent and pathConfidentiality, authentication, or a ranking resultsitemap.xmlHelps search engines discover canonical URLs and their metadataCrawling or indexing of every listed URL Google says a small, well-linked site may not need a sitemap, while larger, newer, or media-heavy sites can benefit from one, and that a sitemap is a hint. llms.txt does not do that discovery job. A sitemap does not do the narrative one. Training and Search controls live elsewhere too. To tell OpenAI not to use crawled content for foundation-model training, configure GPTBot. The [crawler comparison](https://lenvanderhof.com/en/blog/gptbot-vs-oai-searchbot/) separates that switch from ChatGPT Search and from person-triggered fetching. llms.txt can grant or withhold neither permission. ## What belongs in the file Start with the reader, not the format. Which agent, assistant, or retrieval workflow are you helping, and what should it find faster than it would by crawling? A useful file stays small: - the name of the site or section and one honest paragraph on what it is; - a few notes that prevent predictable confusion, such as two products with similar names or a retired API; - canonical public URLs, each with a one-line description; - links to clean text or Markdown versions when you maintain them; - an Optional section for secondary material that would otherwise crowd the main path. This site publishes [`/llms.txt`](https://lenvanderhof.com/llms.txt) and a longer `/llms-full.txt`. Both answered with HTTP 200 and `text/plain` when checked on 2026-09-04. That is a choice made for clients that read such files. It is not evidence that any search engine rewards them. ## Where the file fails The first failure is an audience with no name. A file generated because an audit tool showed an empty checkbox has no operating purpose and no owner. The second is stale guidance. If the map lists retired products, redirected pages, or unpublished drafts, a compliant client follows the wrong route perfectly. Update the file when canonical URLs, access rules, or publication status change. Ownership matters more than generation. The third is duplication without judgment. Dumping every URL into Markdown recreates the navigation problem the file was meant to reduce. Select. Describe. Keep the detail behind the link. The fourth is magical attribution. An answer may cite your page after ordinary web search, a third-party index, a pasted URL, or some other retrieval path. The citation does not prove that llms.txt was read. If you need to know, inspect request logs for the file, or run a controlled test with the client you care about. ## The decision Publish llms.txt when three conditions hold: 1. You can name at least one client or workflow that may use it. 2. The linked material is public, canonical, and useful in machine-readable form. 3. Someone owns the freshness of every link and description. Otherwise, improve the pages themselves. The [citation-readiness audit](https://lenvanderhof.com/en/blog/citation-readiness-audit/) asks whether a URL exposes a clear answer, a name, and support that survives inspection. [What GEO means](https://lenvanderhof.com/en/blog/what-geo-means/) covers the wider job of becoming a source. [The Findability Engine](https://lenvanderhof.com/books/the-findability-engine/) owns the longer treatment; the book is in production and not for sale. Google reads the ordinary pages. So does every other engine. A manifesto in the root cannot rescue an empty one. Cite this:What is llms.txt? A manifesto, not a ranking switch.Len P. van der Hof. [https://lenvanderhof.com/en/blog/what-is-llms-txt/](https://lenvanderhof.com/en/blog/what-is-llms-txt/) · Published 22 September 2026. ## Terminology - [CITATION](https://lenvanderhof.com/glossary/citation/) - [GEO](https://lenvanderhof.com/glossary/geo/) ## Sources 1. [Citation-readiness audit](https://lenvanderhof.com/en/blog/citation-readiness-audit/) 2. [GPTBot vs OAI-SearchBot vs ChatGPT-User](https://lenvanderhof.com/en/blog/gptbot-vs-oai-searchbot/) 3. [What GEO means](https://lenvanderhof.com/en/blog/what-geo-means/) 4. [The Findability Engine](https://lenvanderhof.com/books/the-findability-engine/) 5. [llms.txt on this site](https://lenvanderhof.com/llms.txt) 6. [The /llms.txt file, v2](https://llmstxt.org/) · llms-txt 7. [Optimizing your website for generative AI features on Google Search](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide) · Google Search Central 8. [Learn about sitemaps](https://developers.google.com/search/docs/crawling-indexing/sitemaps/overview) · Google Search Central ## Further reading - [Citation-readiness audit](https://lenvanderhof.com/en/blog/citation-readiness-audit/) - [What GEO means](https://lenvanderhof.com/en/blog/what-geo-means/) - [GPTBot vs OAI-SearchBot vs ChatGPT-User](https://lenvanderhof.com/en/blog/gptbot-vs-oai-searchbot/) - [The Findability Engine](https://lenvanderhof.com/books/the-findability-engine/) About the author ## [Len P. van der Hof](https://lenvanderhof.com/en/authors/len-p-van-der-hof/) Entrepreneur, AI Innovator and Venture Builder Len P. van der Hof builds practical AI systems, digital ventures and evidence-informed tools for founders. ```json { "@context": "https://schema.org", "@graph": [ { "@type": "Person", "@id": "https://lenvanderhof.com/#person", "name": "Len P. van der Hof", "alternateName": [ "Len van der Hof", "L.P. van der Hof", "Leendert Pieter van der Hof" ], "honorificSuffix": "MSc", "url": "https://lenvanderhof.com/", "image": [ "https://lenvanderhof.com/photos/len-portrait-1.jpg", "https://lenvanderhof.com/photos/len-portrait-2.jpg", "https://lenvanderhof.com/photos/len-portrait-3.jpg", "https://lenvanderhof.com/photos/len-portrait-4.jpg", "https://lenvanderhof.com/photos/len-speaking.jpg", "https://lenvanderhof.com/photos/len-hero.jpg" ], "jobTitle": "Entrepreneur, AI Innovator and Venture Builder", "description": "Len P. van der Hof, MSc, is a Dutch entrepreneur and AI innovator in Zwijndrecht. He builds ReasonKit, MindSesh, Undominated.ai, books under his name, the fiction imprint LPH98.lifestyle, and technology ventures through LPH98.ventures. Eleven titles in Systems for the Strategic Self are available now, in English and Dutch.", "address": { "@type": "PostalAddress", "addressLocality": "Zwijndrecht", "addressCountry": "NL" }, "alumniOf": { "@type": "CollegeOrUniversity", "name": "Rotterdam School of Management, Erasmus University" }, "knowsAbout": [ "Artificial intelligence", "AI agents", "Agentic AI systems", "LLM routing", "SEO", "Generative engine optimization", "Answer engine optimization", "Venture building", "Founder performance", "Founder psychology", "Evidence-based decision-making" ], "sameAs": [ "https://www.linkedin.com/in/lenvanderhof/", "https://x.com/LenvanderHof", "https://www.youtube.com/channel/UCTG20buKqYYbitqqf7l3zJA", "https://www.instagram.com/Lenvanderhof/", "https://www.threads.com/@lenvanderhof", "https://github.com/Lenvanderhof", "https://huggingface.co/LPH98", "https://www.npmjs.com/~lenvanderhof", "https://www.goodreads.com/author/show/70983905.Len_P_van_der_Hof", "https://www.amazon.com/author/lenvanderhof", "https://www.bol.com/nl/nl/b/len-p-van-der-hof-msc/609879394/", "https://bsky.app/profile/lenvanderhof.com", "https://mastodon.social/@Lenvanderhof", "https://crates.io/users/Lenvanderhof", "https://cursor.com/@Lenvanderhof", "https://medium.com/@Lenvanderhof", "https://gitlab.com/Lenvanderhof", "https://hub.docker.com/u/lenvanderhof/", "https://dev.to/lenvanderhof", "https://www.facebook.com/Lenvanderhof", "https://soundcloud.com/Lenvanderhof" ], "affiliation": [ { "@id": "https://lenvanderhof.com/#publisher" }, { "@id": "https://lenvanderhof.com/#mindsesh" }, { "@id": "https://lenvanderhof.com/#lifestyle" } ] }, { "@type": "WebSite", "@id": "https://lenvanderhof.com/#website", "url": "https://lenvanderhof.com/", "name": "Len P. van der Hof", "description": "Len P. van der Hof, MSc, is a Dutch entrepreneur and AI innovator in Zwijndrecht. He builds ReasonKit, MindSesh, Undominated.ai, books under his name, the fiction imprint LPH98.lifestyle, and technology ventures through LPH98.ventures. Eleven titles in Systems for the Strategic Self are available now, in English and Dutch.", "inLanguage": [ "en", "nl" ], "publisher": { "@id": "https://lenvanderhof.com/#person" } }, { "@type": "Organization", "@id": "https://lenvanderhof.com/#publisher", "name": "LPH98.ventures", "url": "https://lph98.ventures", "founder": { "@id": "https://lenvanderhof.com/#person" } }, { "@type": "Organization", "@id": "https://lenvanderhof.com/#mindsesh", "name": "MindSesh", "url": "https://mindsesh.net", "founder": { "@id": "https://lenvanderhof.com/#person" } }, { "@type": "SoftwareApplication", "@id": "https://lenvanderhof.com/#reasonkit", "name": "ReasonKit", "url": "https://reasonkit.sh", "creator": { "@id": "https://lenvanderhof.com/#person" } }, { "@type": "SoftwareApplication", "@id": "https://lenvanderhof.com/#undominated", "name": "Undominated.ai", "url": "https://undominated.ai", "creator": { "@id": "https://lenvanderhof.com/#person" } }, { "@type": "Organization", "@id": "https://lenvanderhof.com/#lifestyle", "name": "LPH98.lifestyle", "url": "https://lph98.lifestyle", "founder": { "@id": "https://lenvanderhof.com/#person" } }, { "@type": "ImageObject", "@id": "https://lenvanderhof.com/en/blog/what-is-llms-txt/#primaryimage", "url": "https://lenvanderhof.com/media/generated/blog-hero-llms-txt-v1.1d06121fea07.wide.webp", "contentUrl": "https://lenvanderhof.com/media/generated/blog-hero-llms-txt-v1.1d06121fea07.wide.webp", "representativeOfPage": true }, { "@type": "BreadcrumbList", "@id": "https://lenvanderhof.com/en/blog/what-is-llms-txt/#breadcrumb", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://lenvanderhof.com/" }, { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://lenvanderhof.com/en/blog/" }, { "@type": "ListItem", "position": 3, "name": "SEO, GEO and AEO", "item": "https://lenvanderhof.com/en/blog/category/seo-geo-aeo/" }, { "@type": "ListItem", "position": 4, "name": "What is llms.txt? A manifesto, not a ranking switch", "item": "https://lenvanderhof.com/en/blog/what-is-llms-txt/" } ] }, { "@type": "WebPage", "@id": "https://lenvanderhof.com/en/blog/what-is-llms-txt/#webpage", "url": "https://lenvanderhof.com/en/blog/what-is-llms-txt/", "name": "What is llms.txt? A manifesto, not a ranking switch", "description": "llms.txt is a voluntary Markdown map for agents and retrieval clients that choose to read it. It does not control crawling, replace a sitemap, or move Google rankings. Google says Search ignores it, and that it neither helps nor harms.", "isPartOf": { "@id": "https://lenvanderhof.com/#website" }, "primaryImageOfPage": { "@id": "https://lenvanderhof.com/en/blog/what-is-llms-txt/#primaryimage" }, "breadcrumb": { "@id": "https://lenvanderhof.com/en/blog/what-is-llms-txt/#breadcrumb" }, "inLanguage": "en-GB" }, { "@type": "BlogPosting", "@id": "https://lenvanderhof.com/en/blog/what-is-llms-txt/#article", "mainEntityOfPage": { "@id": "https://lenvanderhof.com/en/blog/what-is-llms-txt/#webpage" }, "headline": "What is llms.txt? A manifesto, not a ranking switch", "description": "llms.txt is a voluntary Markdown map for agents and retrieval clients that choose to read it. It does not control crawling, replace a sitemap, or move Google rankings. Google says Search ignores it, and that it neither helps nor harms.", "datePublished": "2026-09-22T07:00:00.000Z", "author": { "@id": "https://lenvanderhof.com/#person" }, "publisher": { "@id": "https://lenvanderhof.com/#person" }, "image": [ "https://lenvanderhof.com/media/generated/blog-hero-llms-txt-v1.1d06121fea07.square.webp", "https://lenvanderhof.com/media/generated/blog-hero-llms-txt-v1.1d06121fea07.landscape.webp", "https://lenvanderhof.com/media/generated/blog-hero-llms-txt-v1.1d06121fea07.wide.webp" ], "articleSection": "SEO, GEO and AEO", "inLanguage": "en-GB" } ] } ```