# LLMs Full Text

> A reference on llms.txt: the format, v2 of the proposal, examples and tools

Every page has a Markdown version: append `index.html.md` to the page address. The server returns the same version at the page address for a request with the `Accept: text/markdown` header.

## Home

- [llms.txt reference: format, examples and tools](https://llms-full-txt.ru/en/index.html.md): llms.txt is a file at the site root that lists a site's main pages for AI agents. A reference on the v2 format, examples, tools, validation and the evidence on whether it works

## Guides

- [An AI-ready site: llms.txt, markup and crawler access](https://llms-full-txt.ru/en/guides/ai-ready-site/index.html.md): What to do with a site so that search engines, AI models and AI agents can find and understand it - six layers from the server response to measurement
- [GEO and AEO: optimizing a site for AI search](https://llms-full-txt.ru/en/guides/geo-aeo/index.html.md): What GEO and AEO are, where the terms came from, what Google says about them, where llms.txt and structured data fit, and which of the promises can be verified
- [JSON-LD structured data for search and AI](https://llms-full-txt.ru/en/guides/json-ld/index.html.md): What structured data, Schema.org and JSON-LD are, why a site prepared for search and AI needs them, and which markup fits a store, a blog, a forum and a knowledge base
- [What is llms-full.txt and how it differs from llms.txt](https://llms-full-txt.ru/en/guides/llms-full-txt/index.html.md): llms-full.txt is the whole text of the documentation in one file. How it differs from llms.txt, who publishes it, how big it gets and when it is not needed
- [How to measure a site's visibility in AI answers](https://llms-full-txt.ru/en/guides/ai-visibility/index.html.md): What can really be measured in AI search: bot requests in server logs, referrals from AI systems, citations and share of voice. How to do it and where measurement ends
- [Markdown versions of pages for AI agents](https://llms-full-txt.ru/en/guides/markdown-pages/index.html.md): Why a site may serve Markdown versions of pages to AI agents and three ways to do it: a separate .md address, the Accept header and a rel=alternate link
- [Is llms.txt a standard? Status of the proposal](https://llms-full-txt.ru/en/guides/standard-status/index.html.md): What llms.txt is in 2026: a proposal and its v2, who publishes the file, what Lighthouse checks, what is known about its effect on search, and what remains open
- [What is llms.txt? Purpose and file structure](https://llms-full-txt.ru/en/guides/what-is-llms-txt/index.html.md): llms.txt in plain words - what the file is, how it differs from robots.txt and sitemap.xml, who needs it and what not to expect from it
- [GPTBot, ClaudeBot and robots.txt: managing AI crawlers](https://llms-full-txt.ru/en/guides/ai-crawlers/index.html.md): AI bots of OpenAI, Anthropic, Google, Perplexity, Apple, Meta and Yandex: three classes (training, search, user-triggered), which obey robots.txt, and a configuration template
- [Does llms.txt work? What the studies show](https://llms-full-txt.ru/en/guides/does-llms-txt-work/index.html.md): What the Ahrefs, SE Ranking and Common Crawl studies and Google's documentation show - what is confirmed about llms.txt, what is not proven, and what does not follow
- [How to create an llms.txt file: step-by-step guide](https://llms-full-txt.ru/en/guides/getting-started/index.html.md): How to create llms.txt by the second edition of the proposal: pick the main pages, write the file, place it at the site root, check the server response, keep it current
- [llms.txt best practices: what to include and avoid](https://llms-full-txt.ru/en/guides/best-practices/index.html.md): How to make llms.txt useful: page selection, link notes, size, links to Markdown, refreshing, security and typical mistakes found in 584 thousand published files
- [llms.txt validator and checker: files and markup](https://llms-full-txt.ru/en/guides/validation/index.html.md): How to check llms.txt, llms-full.txt, Markdown versions of pages and structured data: status code, content type, structure, links, validators and typical mistakes
- [Lighthouse and llms.txt: what the audit checks](https://llms-full-txt.ru/en/guides/lighthouse/index.html.md): What the llms.txt audit in Lighthouse and PageSpeed Insights checks, when it appeared, what it does not prove, and whether to create the file for the sake of the report
- [llms.txt in WordPress: plugins and manual setup](https://llms-full-txt.ru/en/guides/wordpress/index.html.md): How to get llms.txt on a WordPress site: what Yoast SEO, All in One SEO, Rank Math and a dedicated plugin can do, how they differ, and what to check after switching it on
- [llms.txt and JSON-LD in Webasyst and Shop-Script](https://llms-full-txt.ru/en/guides/webasyst/index.html.md): How to get llms.txt and structured data in Webasyst and Shop-Script: what each app contributes, how files and markup are refreshed, and what to check after installation

## Specification

- [llms.txt file format: syntax and rules](https://llms-full-txt.ru/en/specification/format/index.html.md): The llms.txt format under v2 of the proposal: the one required heading, the order of parts, link lists, files in subpaths, Markdown page versions, and what is left out
- [llms.txt sections: file structure and Optional](https://llms-full-txt.ru/en/specification/sections/index.html.md): How llms.txt sections work under v2 of the proposal - link lists under H2 headings, Optional as a convention, ordering, files for site sections and languages, typical mistakes
- [Discovering llms.txt and Markdown versions of pages](https://llms-full-txt.ru/en/specification/discovery/index.html.md): How an agent finds llms.txt and the Markdown version of a page under the second edition - rel=alternate and rel=describedby, the Link header, files in subpaths
- [llms.txt v2: what changed in the second edition](https://llms-full-txt.ru/en/specification/changes/index.html.md): How v2 of the llms.txt proposal differs from v1: discovery through rel=alternate and rel=describedby, files in subpaths, two Markdown URL forms, the new role of Optional

## Examples

- [llms.txt example: basic files and templates](https://llms-full-txt.ru/en/examples/basic/index.html.md): Sample llms.txt files with commentary for a documentation site, an online store, a blog and a company site - what goes into each section, why, and what to change for your own site
- [llms.txt examples: advanced files explained](https://llms-full-txt.ru/en/examples/advanced/index.html.md): Complex llms.txt setups explained: several languages, versions, monorepo packages and services, the full-text file, a CI build, and real files from well-known sites

## Tools

- [llmstxt CLI: llms.txt and llms-full.txt from a sitemap](https://llms-full-txt.ru/en/tools/llmstxt-cli/index.html.md): llmstxt - a Node.js command-line utility that builds llms.txt and llms-full.txt from sitemap.xml - commands, options, what comes out and what the utility cannot do
- [llmstxt-architect: generating llms.txt with an LLM](https://llms-full-txt.ru/en/tools/llmstxt-architect/index.html.md): llmstxt-architect is a Python utility that crawls a site and writes llms.txt link notes with a language model: running it, options, output, and why to treat it as frozen
- [llm.codes: documentation as clean Markdown for AI](https://llms-full-txt.ru/en/tools/llm-codes/index.html.md): llm.codes turns script-heavy documentation pages into clean Markdown for AI systems: what it does, how it differs from an llms.txt generator, and how to self-host it
- [llms.txt generators: tools and services](https://llms-full-txt.ru/en/tools/generators/index.html.md): What to create llms.txt with: CMS extensions, plugins for documentation generators, command-line utilities and web services, with a note on what is no longer maintained

## Reference

- [llms.txt in Starlight, VitePress, Docusaurus, MkDocs, Nuxt](https://llms-full-txt.ru/en/reference/configuration/index.html.md): How to enable llms.txt in Starlight, VitePress, Docusaurus, MkDocs and Nuxt - a working setup for each, which files the plugin creates and what to check after the build
- [llms.txt vs MCP: the difference and how they relate](https://llms-full-txt.ru/en/reference/mcp-relationship/index.html.md): How llms.txt differs from the Model Context Protocol (MCP): a file an agent reads versus a protocol with tool calls. The mcpdoc bridge, security and which to choose
- [Who publishes llms.txt: a registry of sites](https://llms-full-txt.ru/en/reference/adoption/index.html.md): A registry of sites checked for llms.txt, llms-full.txt and Markdown versions of pages, with the measurement date, adoption estimates and well-known sites without the file
- [Glossary: llms.txt, GEO, AEO and AI crawler terms](https://llms-full-txt.ru/en/reference/glossary/index.html.md): Short definitions of AI search terms: GEO, AEO, LLMO, AI SEO, AI Overviews, agent, crawler, llms.txt, structured data, Schema.org, JSON-LD, with origin and status
- [Paying for Claude and ChatGPT from Russia](https://llms-full-txt.ru/en/reference/from-russia/index.html.md): How to pay for AI models, code editors, hosting, domains and SEO services from Russia, and what to do when a service does not open

## Prompts

- [Prompts for llms.txt](https://llms-full-txt.ru/en/prompts/index.html.md): Three ready-to-use prompts: write llms.txt, audit an existing file and prepare site content for AI systems
- [Generate llms.txt](https://llms-full-txt.ru/en/prompts/generate-llms-txt/index.html.md): Prompt for AI-generating an llms.txt file from a project description
- [Audit llms.txt](https://llms-full-txt.ru/en/prompts/audit-llms-txt/index.html.md): Prompt for reviewing and improving an existing llms.txt file
- [Optimize content for AI](https://llms-full-txt.ru/en/prompts/optimize-for-ai/index.html.md): Prompt for optimizing website content for AI search and citations

## Files

- [llms-full.txt](https://llms-full-txt.ru/en/llms-full.txt): The whole reference text in one file
- [llms-small.txt](https://llms-full-txt.ru/en/llms-small.txt): The start of every page, a short version
- [rss.xml](https://llms-full-txt.ru/en/rss.xml): Blog feed, RSS
- [feed.json](https://llms-full-txt.ru/en/feed.json): Blog feed, JSON Feed
- [Русская версия](https://llms-full-txt.ru/llms.txt): Тот же справочник на русском

## Optional

- [llms.txt and AI search blog](https://llms-full-txt.ru/en/blog/index.html.md): The chronicle of 2026: what happened, what the studies measured and what it means for a site owner
- [llms.txt in autumn 2026: what is known](https://llms-full-txt.ru/en/blog/state-of-llms-txt-autumn-2026/index.html.md): A summary of the year - the second edition of the proposal, the Lighthouse check, Google’s position, studies of requests and file quality. What is confirmed, what is not proven and what to do with a site
- [Lighthouse 13.5: llms.txt becomes one of the discovery points](https://llms-full-txt.ru/en/blog/lighthouse-13-5-agent-discovery/index.html.md): In Lighthouse 13.5.0 the llms.txt check is grouped with other ways an agent discovers a site - what changed in the report and what stayed the same
- [Mintlify: agents request documentation twice as often as people](https://llms-full-txt.ru/en/blog/mintlify-agents-outnumber-people/index.html.md): A documentation platform’s report for August 2026 - 257 million agent requests against 131 million human page loads. What it says about documentation and what it does not say about other sites
- [IETF AIPREF: the AI preference vocabulary is still a draft](https://llms-full-txt.ru/en/blog/ietf-aipref-drafts/index.html.md): The IETF AIPREF working group updated the draft vocabulary a site can use to say whether its content may be used for training and answers - what is in it and why it is too early to rely on it
- [Common Crawl analyzed 584 thousand llms.txt files](https://llms-full-txt.ru/en/blog/common-crawl-584k-llms-txt/index.html.md): The first analysis of llms.txt content from an open web crawl - 68% of files made by a generator, 23% without a single link, and 40% of successful responses turned out to be an HTML page
- [The second edition of llms.txt is out](https://llms-full-txt.ru/en/blog/llms-txt-v2/index.html.md): On August 10, 2026, the second edition of the llms.txt proposal was published - discovery relations, files in subpaths, two forms of Markdown addresses and a new role for the Optional section
- [Mintlify test: with llms.txt an agent hits fewer missing pages](https://llms-full-txt.ru/en/blog/mintlify-markdown-benchmark/index.html.md): Mintlify compared four documentation formats on 20 sites and 2,400 runs - what changed, what stayed the same and why the source has to be treated as an interested party
- [Chrome describes how to prepare a site for agents](https://llms-full-txt.ru/en/blog/chrome-agent-ready-toolkit/index.html.md): The Chrome blog published an agent-ready toolkit - the Agentic Browsing category in Lighthouse, WebMCP and DevTools for agents. The post does not mention llms.txt
- [Ahrefs: 97% of llms.txt files were never requested](https://llms-full-txt.ru/en/blog/ahrefs-llms-txt-study/index.html.md): The Ahrefs study of 137 thousand domains - how many sites publish llms.txt, who requests it and why the numbers need to be read with caveats
- [Google documents it: Search does not use llms.txt](https://llms-full-txt.ru/en/blog/google-search-ignores-llms-txt/index.html.md): What exactly the Google guide on AI features in Search says, what it covers and what it does not, and how it fits with the Lighthouse check
- [Lighthouse starts checking llms.txt](https://llms-full-txt.ru/en/blog/lighthouse-checks-llms-txt/index.html.md): In Lighthouse 13.3.0 the llms.txt check is on by default - what exactly it looks at, why an empty file passes and what it does not prove
- [llms.txt in 2026: From Experiment to Standard](https://llms-full-txt.ru/en/blog/llms-txt-2026/index.html.md): How llms.txt evolved from Jeremy Howard's idea to 10% adoption among 300K domains. What changed and what's next.
- [AI crawlers guide: who to allow, who to block](https://llms-full-txt.ru/en/blog/ai-crawlers-guide/index.html.md): Complete guide to AI crawlers in 2026 — GPTBot, ClaudeBot, Google-Extended. How to configure robots.txt for AI bots.
- [Cloudflare serves Markdown to agents instead of HTML](https://llms-full-txt.ru/en/blog/cloudflare-markdown-for-agents/index.html.md): Cloudflare turned on page-to-Markdown conversion by the Accept header - how it works, how much it saves and what stays on the site owner’s side
- [Web Almanac: two sites in a hundred have llms.txt](https://llms-full-txt.ru/en/blog/web-almanac-2025-llms-txt/index.html.md): The SEO chapter of Web Almanac 2025 counted llms.txt across the HTTP Archive crawl for the first time - 2.1% of sites, and most files come from WordPress plugins