llms.txt is a proposed Markdown file at the root of a website (/llms.txt) that gives language models and AI agents a short, curated overview of the site’s most important content. Jeremy Howard published the proposal on llmstxt.org on September 3, 2024 and released a revised version 2 in August 2026. It is a community proposal, not a standard from a body like the IETF or W3C.
At a glance
- Type
- file (Markdown)
- Status
- proposal by Jeremy Howard (Sep 3, 2024), version 2 from Aug 10, 2026
- Location
/llms.txtor in a subpath- Affects
- language models and AI agents; Google Search ignores the file, according to Google
- Docs
- llmstxt.org
Last checked:
How is an llms.txt file structured?
The proposal defines a fixed order. The only required element is an H1 heading with the name of the site or project. It can be followed by a short summary in a blockquote, further paragraphs with details, and sections under H2 headings that contain lists of Markdown links, each with an optional note. By convention, a section named “Optional” holds secondary links an agent can skip when it needs a shorter context.
The proposal also suggests offering clean Markdown versions of important pages, either with .md appended (page.html.md) or with .md replacing the file extension. Version 2 adds link relations so agents can find them: rel="alternate" type="text/markdown" for the Markdown version and rel="describedby" for the applicable llms.txt, as HTML <link> elements or HTTP Link headers. The file can sit in a subdirectory, for example /docs/llms.txt, and then covers the URLs below that path. Where several files apply, the most specific one wins.
llms.txt does not control access. Crawling permissions stay with robots.txt, and sitemap.xml remains the complete list of URLs. llms.txt is a curated reading list on top of both.
| File | Standard or proposal? | Location | Purpose | Who reads it (documented) |
|---|---|---|---|---|
| robots.txt | IETF standard: RFC 9309 (September 2022) | / | tells crawlers which URLs they may fetch; per the RFC not a form of access authorization | Crawlers; Google's common crawlers always respect it for automatic crawls |
| llms.txt (this term) | Proposal (Jeremy Howard, 2024; version 2 from August 2026) | / or in a subpath | Markdown overview linking to Markdown versions of pages, for AI agents | per the proposal mainly coding agents; Google Search ignores it, says Google; Lighthouse only checks the fetch |
| llms-full.txt | no specification; not part of the llms.txt proposal, a convention of individual vendors (e.g. Mintlify) | / (Mintlify also serves /.) | entire documentation as Markdown in one file | no reader documented; Google Search doesn't use such files, says Google |
| ai.txt | Individual IETF Internet-Draft (June 2026, expires 2026-12-14), not a standard; predecessor by Spawning (2023) | /. (draft), / (Spawning) | AI usage preferences (training, scraping, indexing, caching), licensing, attribution | no reader documented in primary sources; Google Search doesn't use 'AI text files', says Google |
TDMRep (tdmrep.) | W3C Community Group Final Report (2024-05-10), not a W3C standard | /., HTTP header tdm-reservation or HTML meta tag | machine-readable reservation of text and data mining rights (Art. 4 DSM Directive) | parties performing text and data mining (per the specification) |
| security.txt | RFC 9116 (April 2022, informational, not standards track) | /. | contact for reporting security vulnerabilities; required fields Contact and Expires | Security researchers |
| ads.txt | IAB Tech Lab specification, version 1.1 (August 2022) | / on the root domain, subdomains as needed | declares the companies authorized to sell the site's ad inventory | advertising systems and buyers (ad system crawlers) |
| humans.txt | Initiative (humanstxt.org), no formal specification | / next to robots.txt, optionally linked via rel="author" | names the people who contributed to the website | people who want to know who is behind the website |
Only robots.txt, security.txt and ads.txt are based on a finalised specification (IETF or IAB Tech Lab). Google states that Google Search doesn't use new machine-readable files or 'AI text files' and ignores llms.txt files, which neither help nor harm Search visibility. TDMRep is a technical way to express the reservation under Art. 4 of Directive (EU) 2019/790. Not legal advice. Sources: RFC 9309: Robots Exclusion Protocol; Google: Overview of Google crawlers and fetchers (last updated 2026-06-12); The /llms.txt file, v2 (llmstxt.org); llmstxt.org: Changes (v2, August 2026); Google Search Central: Optimizing for generative AI features (last updated 2026-07-10); Chrome for Developers: Lighthouse llms.txt audit (2026-05-05); Mintlify: llms.txt and llms-full.txt; IETF Internet-Draft draft-car-ai-txt-wellknown-00 (2026-06-12); W3C TDMRep Community Group: TDM Reservation Protocol, Final Report 2024-05-10; RFC 9116: A File Format to Aid in Security Vulnerability Disclosure; IAB Tech Lab: ads.txt; IAB Tech Lab: ads.txt Specification Version 1.1 (GitHub); humanstxt.org. Last checked: .
Example
# Example Running Co.
> Maker of running shoes. The site has product specs, size charts and care guides.
## Products
- [Running shoes](https://www.example.com/running-shoes.md): all models with technical data
- [Size chart](https://www.example.com/sizes.md): US, UK and EU conversion
## Optional
- [Company history](https://www.example.com/about.md)
Does Google use llms.txt?
No. In its guide to generative AI features, Google says that machine-readable AI text files are not needed to appear in Google Search and that such files neither help nor harm a site’s visibility or rankings.
Lighthouse includes an llms.txt audit in its Agentic Browsing category. It only flags a page when requesting the file returns a server error. A missing file (404) is marked as not applicable, because the file is optional.
FAQ
Is llms.txt actually used? According to reports, mostly by developer documentation sites, whose content is read by coding assistants and agents. For Google Search it has no effect. A measurable effect on mentions in AI answers has not been shown so far.
Is llms.txt mandatory? No. It is a voluntary proposal. Lighthouse explicitly treats a missing file as not applicable.
What is llms-full.txt? A common variant that bundles the full text of a site or its documentation into one Markdown file. The proposal on llmstxt.org does not define it, in version 2 either.
Sources
- The /llms.txt file – llmstxt.org (Jeremy Howard, published 2024-09-03, v2 modified 2026-08-10)llmstxt.org
- Google's guide to optimizing for generative AI features on Google Search – Google Search Central (updated 2026-07-10)developers.google.com
- llms.txt – Lighthouse Agentic Browsing audit, Chrome for Developersdeveloper.chrome.com
- Changes – llmstxt.org (v1 to v2, August 2026)llmstxt.org
- RFC 9309: Robots Exclusion Protocol – IETFrfc-editor.org
Last updated: