llms.txt Generator

This llms.txt generator builds an llms.txt file for your site: a short Markdown file that tells AI agents what your site is and where its most useful pages are. Enter your site’s name and summary, add sections of links, or import them from your XML sitemap, and the file is written in the format the llms.txt proposal sets out. Every change is checked as you type, and nothing leaves your browser.

How to create an llms.txt file

• Name your site and summarize it. The name is the only required part. The summary is one or two sentences with the key facts an agent needs first.
• Add sections of links, such as Docs, Guides, or Policies, with a short note on what each page covers. Or click Import pages and paste your sitemap.
• Read the checks and fix anything flagged.
• Copy or download llms.txt and upload it to the root of your site, so it opens at yoursite.com/llms.txt.

What is llms.txt?

llms.txt is a proposal, first published by Jeremy Howard of Answer.AI in 2024, for a plain-text file that gives large language models a curated map of a website. Web pages are full of navigation, scripts, and ads, and a whole site rarely fits in a model’s context. An llms.txt file gives an agent the essentials in one small, readable file instead. It’s a community proposal, not a web standard, and no search engine or AI company is required to read it.

The format has a fixed order:

• An H1 with the site or project name. This is the only required part.
• A blockquote with a short summary.
• Optional details: paragraphs or lists, but no headings.
• H2 sections, each containing a list of links in the form - [Name](URL): notes.

A section called Optional is a convention for links an agent can skip when it needs a shorter context.

llms.txt example

Here is the example file this generator builds when you click Load example, shortened:

# Northpeak Trail Planner

> Northpeak Trail Planner is a web app for planning hiking and trail-running routes, with offline maps, elevation profiles, and weather alerts.

The API uses REST and JSON, and needs an API key from account settings.

## Docs

- [Getting started](https://www.northpeak.example/docs/getting-started/): Create an account and plan your first route
- [Offline maps](https://www.northpeak.example/docs/offline-maps/): Download areas and use them without signal

## Optional

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

The llms.txt generator handles the details that are easy to get wrong by hand. It joins the summary into one line, because the reference parser reads only the first line of the blockquote. It turns headings in the details into bold text, since a heading there would start a new section. It encodes spaces and parentheses in URLs so links don’t break, and it names links from their URLs when you leave the name blank.

Does llms.txt help SEO?

No, not for Google. In June 2026, Google added a section to its AI search optimization guide saying that Google Search doesn’t use llms.txt or other AI text files, and that adding one “won’t harm (nor help)” your visibility or rankings. An llms.txt file won’t get you into AI Overviews either. Treat any tool or service that promises rankings from llms.txt with caution.

Other AI crawlers rarely ask for it. Ahrefs looked at logs from 137,000 domains in May 2026 and found that 97% of llms.txt files received no requests at all, and AI bots made only about a fifth of the requests that did arrive. The main readers were coding agents, such as Claude Code, which look up documentation while they work.

So who should make one? It’s most useful for developer documentation, APIs, software products, and knowledge bases, where people ask AI assistants and coding tools to read your docs for them. For a typical business site or blog, it’s a cheap, low-risk extra, not a priority. Your crawl rules, structured data, and clear content still matter far more.

Start from your sitemap

Click Import pages and paste your XML sitemap, or upload it. The llms.txt generator groups pages into sections by their first folder, names each link from its URL, and puts a folder’s own page, such as /docs/, at the top of its section. It also accepts a plain list of URLs, one per line, with an optional name and notes in the form Name | URL | Notes. Up to 1,000 URLs are imported at once.

A sitemap lists every page, but an llms.txt file works best as a short, curated list. After importing, remove pages agents don’t need, such as tag archives and thin posts, and add a note to the ones that remain. If you paste a sitemap index, the generator asks for one of the sitemaps it links to instead.

Which pages to include

• Docs and guides that explain how your product works.
• API references and authentication pages.
• Pricing, plans, and policies, such as returns, shipping, or support hours.
• About and contact pages that say who you are.
• Secondary pages, such as the changelog or older guides, in an Optional section.

The checks warn you about duplicate links, sections with the same heading, empty sections, and files with more than 300 links or 50,000 characters, which can be too big for an agent’s context.

Links to Markdown versions

The proposal also suggests that sites serve a clean Markdown copy of each page at the same URL with .md added, such as page.html.md, or index.html.md for a URL without a file name. Documentation platforms such as Mintlify and GitBook do this automatically. If your site does too, open Options and choose how your Markdown URLs are formed. Only links on your own site are changed. Leave this off if you don’t serve Markdown copies, or agents will follow links to pages that return errors.

Where to upload llms.txt

Put the file at the root of your site, so it opens at https://www.example.com/llms.txt. A file in a folder, such as /docs/llms.txt, covers only the pages under that folder, which suits a docs section on a larger site.

On WordPress, recent versions of Yoast SEO and Rank Math can generate an llms.txt file for you. Use one source: if a plugin already serves the file, edit it there or turn the feature off before uploading your own.

The Discovery tags tab gives you an optional HTML link tag and HTTP header, which point agents to the file from any page it covers.

llms.txt vs robots.txt

	robots.txt	llms.txt
Purpose	Tells crawlers what they may access	Tells agents what to read first
Format	Crawl rules	Markdown
Status	Internet standard (RFC 9309)	Community proposal
Controls access	Yes, for crawlers that follow it	No

An llms.txt file doesn’t block or allow anything. To control which AI crawlers can use your content, use the AI Crawler robots.txt Generator, and make sure the pages you list aren’t blocked by testing them in the robots.txt Tester.

Check an existing llms.txt file

Paste a file you already have into Import pages. It loads into the form, and the checks show what to fix: a missing name, a summary split over several lines, headings in the wrong place, or stray text inside a section. Notes written with a dash instead of a colon are converted. Files with extra content, such as llms-full.txt, aren’t part of the proposal itself, so they’re best kept separate.

Once your llms.txt file is live, improve the pages it links to: check their structure with the Heading Structure Checker and their structured data with the JSON-LD Validator.