llms.txt Generator
Build an llms.txt file from a form, in the layout the proposal describes. Google Search ignores the file, so it will not change rankings or AI Overviews; it is for AI tools that fetch it on purpose.
# Example Company > Example Company provides enterprise software solutions for project management and team collaboration. ## Products - [Project Manager Pro](https://example.com/products/project-manager): AI-powered project management for teams of all sizes - [Team Chat](https://example.com/products/team-chat): Real-time messaging with smart threading and search ## Documentation - [Getting Started Guide](https://example.com/docs/getting-started): Set up your workspace in under 5 minutes - [API Reference](https://example.com/docs/api): Complete REST API documentation with code examples
# Example Company > Example Company provides enterprise software solutions for project management and team collaboration. ## Products - [Project Manager Pro](https://example.com/products/project-manager): AI-powered project management for teams of all sizes - [Team Chat](https://example.com/products/team-chat): Real-time messaging with smart threading and search ## Documentation - [Getting Started Guide](https://example.com/docs/getting-started): Set up your workspace in under 5 minutes - [API Reference](https://example.com/docs/api): Complete REST API documentation with code examples
How to generate your llms.txt
From a site name to a file served at yoursite.com/llms.txt.
Enter the site name and summary
The name becomes the H1, the only part the llms.txt proposal requires. The summary becomes the blockquote under it: a sentence or two on what the site is and who it is for.
Group your key pages into sections
Each section becomes an H2 heading over a list of links, such as Docs, Products or Guides. By the proposal's convention, a section named Optional holds material a reader can skip.
Add each page
Give each page a title, its full URL and, if it helps, a short note on what it covers. A page with neither a title nor a URL is left out of the file.
Copy it and publish at /llms.txt
Save the output as llms.txt in your site root, so it loads at yoursite.com/llms.txt, then open that address to check it shows as plain text.
What is llms.txt, and does Google use it?
llms.txt is a Markdown file at the root of a website that lists the site's most useful pages, with a line on each, for a language model to read. Jeremy Howard published the proposal at llmstxt.org on 3 September 2024. Google Search does not use it. Google's guide to optimizing for generative AI search says that keeping one "will neither harm nor help your site's visibility or rankings in Google Search, as Google Search ignores them," a note Google added on 15 June 2026, according to its documentation updates log.
That covers Google's AI answers too. Its page on AI features and your website says you do not need "new machine readable files, AI text files, or markup to appear in these features," meaning AI Overviews and AI Mode. What gets a page into them is being indexed and eligible to show a snippet, and our guide to AIO, AEO and GEO covers the rest of that work.
What goes in an llms.txt file?
The proposal defines a short, fixed layout. An H1 with the name of the site or project is the only required part. Under it come an optional blockquote summarizing the site, optional paragraphs of context, and any number of H2 sections, each a Markdown list of links with an optional note after each one. A section titled Optional is, by convention, for secondary material that can be dropped when space is short. The proposal also suggests offering a clean Markdown copy of important pages at the same address with .md added.
The generator above writes the H1, the blockquote and the H2 link lists, with each link as - [Title](URL): note. It does not write the Markdown page copies, and it does not produce llms-full.txt, a single file holding the full text of a documentation site. That file is a convention that documentation platforms such as Mintlify generate automatically, not part of the proposal.
Who reads llms.txt?
Agents and tools that look for it on purpose, and people who paste it into a chat. The proposal says its author expected the file to be "mainly useful for inference rather than training": read when someone asks a model about a site, not swept up by a crawler building a training set. Chrome's Lighthouse now looks for the file in its agentic browsing audits, describing it as "a machine-readable summary of a website's content, specifically designed for LLMs and AI agents." It flags a server error when fetching the file and marks a missing one as not applicable rather than a failure. OpenAI and Anthropic each publish one for their developer documentation (OpenAI's, Anthropic's), which is where a compact map a developer can hand to a model is most obviously useful.
Publishing a file is not the same as reading other sites' files. OpenAI's page on its crawlers explains how to control OAI-SearchBot and GPTBot with robots.txt and does not say either one reads llms.txt. If you want to know whether anything fetches yours, your server logs will show requests for /llms.txt. A request shows the file was fetched, not that it changed an answer.
How is llms.txt different from robots.txt?
A robots.txt file gives crawlers rules about what not to fetch, and it is a formal standard, RFC 9309, published by the IETF in September 2022, though even the standard says its rules "are not a form of access authorization." llms.txt gives no instructions at all: it is a reading list. To keep an AI company's crawler off your site, or let its search crawler in, you still use robots.txt with the user-agent names each company documents, such as GPTBot for OpenAI's training crawler and OAI-SearchBot for ChatGPT search. The free robots.txt validator checks that file line by line for syntax errors.
Is an llms.txt file worth adding?
For a documentation site, an API or a software product, yes, because it costs little: the file gives developers and agents a clean map to paste into a model, and platforms like Mintlify already generate one. WordPress sites can switch one on in Yoast SEO, free, and Wix generates and maintains one for upgraded sites with a custom domain. For a local business or a small brochure site, the file is harmless and close to pointless.
Either way, it is not where AI visibility comes from. Pages that Google can index and quote, that answer a question plainly and cite their sources, do that work, and none of it needs a new file. If you spend an hour on llms.txt, spend the next ten on the pages it lists.
llms.txt questions.
What the file does, who reads it, and where it goes.
Does Google use llms.txt?
No. Google's guide to optimizing for generative AI search says Google Search ignores llms.txt files, so keeping one will neither help nor harm your visibility or rankings. Google added that note on 15 June 2026. Its page on AI features also says no AI text files are needed to appear in AI Overviews or AI Mode.
Will llms.txt get my site into ChatGPT or Perplexity answers?
Do not count on it. OpenAI's documentation on its crawlers explains how to control them with robots.txt and does not say they read llms.txt. The proposal itself expects the file to be read mainly when someone asks a model about a site, so treat it as a convenience for agents rather than a route into answers.
Where do I put the llms.txt file?
At the root of your domain, so it loads at yoursite.com/llms.txt. In Next.js and Vite that means the public folder; on Apache or Nginx, the document root. Yoast SEO can generate the file for WordPress sites for free, and Wix generates one automatically for upgraded sites with a custom domain.
What is the difference between llms.txt and robots.txt?
robots.txt is a published standard, RFC 9309, that tells crawlers which URLs not to fetch, and both Google and OpenAI document how to control their crawlers with it. llms.txt is a proposed reading list with no rules in it. To block or allow an AI crawler, use robots.txt.
Is llms.txt an official standard?
No. It is a proposal Jeremy Howard published at llmstxt.org on 3 September 2024, not an IETF or W3C standard. Its use is strongest on documentation sites: OpenAI and Anthropic publish one for their developer docs, and Chrome's Lighthouse checks for the file in its agentic browsing audits.
Should I also make an llms-full.txt?
Only if you run documentation that people will want to load into a model whole. llms-full.txt, a single file with the full text of a docs site, is a convention that platforms such as Mintlify generate automatically; the llms.txt proposal does not define it. This generator writes llms.txt only.
What actually gets a page into AI answers?
Mostly the same things that get it into search results. Our guide to AIO, AEO and GEO covers how AI answers pick their sources and how to measure whether yours are cited.
What to do next.
Run these next
All 25- AIO Readiness CheckerCheck a page for noindex and snippet blocks, valid schema and the structure AI answers quote from
- Schema Markup GeneratorGenerate JSON-LD structured data for articles, products, FAQs, and more
- AI Content OptimizerOptimize content for topical depth, readability, and AI citations
- Robots.txt ValidatorValidate your robots.txt syntax and crawl directives
Read next
Rather have it done?
AI visibility report, $49
How often ChatGPT, Gemini and Perplexity name you and three rivals, with the margin of error. From files you export, back within 8 hours.
See the audit