llms.txt Generator

Write an llms.txt file that gives AI assistants a curated, Markdown map of your site — project name, summary, key pages and optional extras — following the llmstxt.org proposal.

Runs in your browser

About the site

Becomes the H1 — the only required element.

Sections & links

One link per line: Title | https://url | optional note. A bare URL also works.

Optionalskippable
Links here can be skipped when an assistant needs a shorter context.

Checks

    Webflow: upload the file under Site settings › SEO › LLMs.txt and publish — it is served at yourdomain.com/llms.txt on your custom domain (not on the .webflow.io staging domain).

    Your data never leaves your computer. All processing happens 100% locally in your browser.

    How to use the llms.txt Generator

    1. Enter your site name and a one- or two-sentence summary. Add details an assistant should know, such as your product’s core concepts.
    2. Create sections (e.g. Docs, Products, Policies) and add one link per line as Title | URL | note.
    3. Put nice-to-have pages in the Optional section so tools can drop them when context is tight.
    4. Check the preview, download llms.txt and publish it at your domain root, e.g. https://example.com/llms.txt.

    What is llms.txt?

    llms.txt is a proposed convention, published by Jeremy Howard at llmstxt.org in 2024, for a Markdown file at the root of a website that gives large language models a concise, curated overview of the site and links to its most useful pages. The idea is that an assistant answering a question about your product can read one small, clean file instead of parsing navigation menus, cookie banners and JavaScript-heavy HTML.

    An honest look at what it does (and doesn’t) do

    llms.txt is an emerging proposal, not a standard. It isn’t part of any W3C or IETF specification, Google has said it doesn’t use it for Search, and it is not a ranking factor. Most AI crawlers don’t request it routinely; it is mainly read when a developer or tool explicitly points an assistant at it — which is why it is popular for documentation sites, APIs and developer tools. It also doesn’t control access: to allow or block AI crawlers, use robots.txt. Creating one takes minutes and costs nothing, so it is a reasonable low-effort addition — just don’t expect traffic from it.

    The format

    The file uses plain Markdown in a fixed order:

    1. An H1 with the project or site name — the only required part.
    2. A blockquote with a short summary.
    3. Optional paragraphs or lists with more detail (no headings).
    4. Zero or more H2 sections, each containing a list of links in the form - [Title](https://url): optional notes.
    5. A section titled exactly Optional for secondary links that can be skipped when a shorter context is needed.
    # Acme Analytics
    
    > Privacy-friendly web analytics for small teams.
    
    ## Docs
    - [Quick start](https://acme.com/start): Setup
    
    ## Optional
    - [Changelog](https://acme.com/changelog)

    The proposal also suggests offering Markdown versions of pages (the same URL with .md appended) and some sites publish an llms-full.txt containing the full text of their docs; both are optional.

    Tips for a useful file

    • Link to pages that answer real questions — docs, pricing, comparisons, policies — not every blog post. Your XML sitemap already lists everything.
    • Write link notes that explain when a page is useful (“Rate limits and error codes”).
    • Keep it current. A stale llms.txt pointing at moved pages is worse than none; pair it with the Redirect Generator when URLs change.
    • See which AI crawlers can reach your site, and whether an llms.txt is detected, with the AI Crawler Checker.

    Tools that pair well with the llms.txt Generator

    • Schema Markup Generator — Pick a schema type, fill in the form and copy ready-to-paste JSON-LD.
    • SEO Checker & Site Audit — Paste a URL to run up to 70 on-page SEO checks in seconds.
    • Meta Tag Checker — See exactly how Google is likely to display your page: title and description measured in pixels, desktop and mobile previews, and every meta tag in the <head>.
    • Heading Checker — Visualise the heading outline of any page.

    Frequently asked questions

    Does llms.txt improve my SEO or Google rankings?
    No. Google has stated it doesn’t use llms.txt, and no major search engine treats it as a ranking signal. It is a convenience file for AI tools that choose to read it.
    Where should I put llms.txt?
    At the root of your domain, e.g. https://example.com/llms.txt, served as plain text (UTF-8). Webflow users can upload it in Site settings › SEO › LLMs.txt.
    What is the difference between llms.txt and robots.txt?
    robots.txt tells crawlers what they may access. llms.txt is a curated reading list for AI assistants; it grants or blocks nothing.
    What is llms-full.txt?
    An informal companion file some sites publish containing the complete text of their documentation in one Markdown file, so an assistant can load everything in one request. It is not part of the core proposal.
    Do I need a section called “Optional”?
    No, it is optional itself. If present, the proposal says links in a section titled “Optional” can be skipped when a shorter context is needed.

    Related tools