Free tools

llms.txt checker and generator

Check an existing llms.txt against the format in the spec and test the links it lists, or build a clean file from your own pages. Below the tools: who reads the file today, according to the companies themselves.

By Adem ÇakalPublished 4 sources

Check an llms.txt

We fetch /llms.txt, check it against the spec's format and try up to 8 of the links it lists, one at a time.

Short answer

llms.txt is a markdown file at /llms.txt that gives AI tools a short map of your site. Google says its Search ignores the file, so it will not move rankings or AI Overviews. It is still worth five minutes if developers or AI agents use your docs, and it costs nothing if you keep it accurate.

What a valid file looks like

The spec asks for very little. Only the first line is required; the rest is convention that makes the file easy for a model to read.

PartRequired?Format
Site or project nameYesAn H1: # Name
SummaryRecommendedA blockquote right under the H1: > One or two sentences
DetailsOptionalParagraphs or lists, but no headings
File listsOptionalH2 sections, each with - [name](url): notes lines
Optional sectionConventionAn H2 named Optional for links an agent may skip
# Acme Analytics

> Privacy-first web analytics for SaaS teams. No cookies, EU hosting.

## Docs

- [Quick start](https://acme.example/docs/start): install the script in 2 minutes
- [API reference](https://acme.example/docs/api): REST endpoints and rate limits

## Product

- [Pricing](https://acme.example/pricing): plans from $9/month

## Optional

- [Changelog](https://acme.example/changelog)

The current version of the spec also suggests a clean markdown copy of useful pages at the same address plus .md, for example /docs/start.md, so an agent can read the page without navigation and scripts.

Who actually reads llms.txt

ReaderWhat the company says
Google Search, AI Overviews, AI ModeIgnores it. Google's guide says creating the file "will neither harm nor help" visibility in Search.
Chrome LighthouseAn optional audit in the experimental agentic browsing category. It flags server errors when fetching the file and marks a missing file (404) as not applicable.
OpenAI, Anthropic, Perplexity crawlersTheir crawler documentation describes robots.txt controls and does not mention llms.txt. If an agent reads your file, your server log is the only proof.

That is the honest state in November 2026: a convention with some readers, not a search signal. Anyone selling llms.txt as a way to rank in ChatGPT or Google is ahead of the evidence.

Mistakes the checker catches most often

  • An HTML page at /llms.txt. Many site builders answer every unknown address with a normal page and HTTP 200. To a tool that looks like a file full of navigation code. The checker treats that as "no llms.txt".
  • No H1 on the first line. The only required part. Files that start with a paragraph or a comment fail it.
  • Dead links. Files written once and never updated point at renamed pages. We test up to eight links so you can see if the map still matches the site.
  • A dump of the sitemap. Hundreds of links with no notes. Keep the file short enough to read in one pass; your sitemap already lists everything.
  • Wrong content type. Serve it as text/plain or text/markdown, not as an HTML or download type.

Build an llms.txt

Where to put it on common platforms

  • WordPress: upload the file to the site root over SFTP or your host's file manager, or let an SEO plugin serve it. Step by step in our WordPress guide.
  • Next.js: put llms.txt in the public/ folder; it is served from the root as is.
  • Hosted builders (Webflow, Framer, Wix, Shopify): most do not let you place arbitrary files at the root. Check your builder's settings for a custom file or redirect option before you spend time on the content.

Questions people ask

Does llms.txt help my Google rankings or AI Overviews?

No. Google's AI optimization guide says Google Search ignores llms.txt files, so they neither help nor harm visibility or rankings in Google Search.

Is there any reason to have one, then?

It is cheap to keep, and tools other than Google Search may read it: coding assistants, documentation agents and browser agents. Chrome's Lighthouse added an optional llms.txt audit in its experimental agentic browsing category. Treat it as a small courtesy file, not an SEO lever.

Where should the file live?

At the root of the site, https://yoursite.com/llms.txt. The current spec also allows a file under a subpath such as /docs/llms.txt that covers only that section.

Should it list every page on my site?

No. It is a curated map. List the pages that explain what you do, your key docs or guides, and pricing. Put secondary links under an H2 named Optional so an agent can skip them when it is short on context.

Sources

  1. llms.txt proposal and specification (Jeremy Howard, v2), accessed 2026-11-12.
  2. Google Search Central: AI optimization guide, accessed 2026-11-12.
  3. Chrome for Developers: Lighthouse llms.txt audit, accessed 2026-11-12.
  4. Search Engine Journal: Google's llms.txt guidance depends on which product you ask (May 20, 2026), accessed 2026-11-12.