llms.txt is a proposed standard for a Markdown file at the root of a website that gives large language models a curated, machine-readable map of your most important content. It helps AI tools find and cite the right pages instead of guessing from raw HTML.

Where do I put the llms.txt file?

Host it at the root of your domain so it resolves at https://yoursite.com/llms.txt, and serve it with a text/plain content type. Many sites also publish an llms-full.txt with the full text content for deeper context.

What is the difference between llms.txt and robots.txt?

robots.txt tells crawlers which paths they may or may not fetch, while llms.txt curates and describes your best content for AI models to read and cite. They serve different goals and you can publish both.

What format does llms.txt use?

It uses Markdown. The file starts with an H1 title, an optional blockquote summary, then H2 sections containing bullet lists of links written as Markdown link syntax with an optional note after a colon.

Is my site data sent anywhere?

No. The builder assembles the llms.txt entirely in your browser from the fields you fill in. Nothing is uploaded, so you can draft the file for an unreleased site safely.

What is the llms.txt File Builder?

Creates a properly formatted llms.txt file with site description, key pages, content areas, and AI-readable context about your product, following the llms.txt standard. Add links with titles and notes, then copy. It runs free in your browser on Gera Tools, with nothing uploaded.

llms.txt File Builder

Name: llms.txt File Builder
Creator: Gera Tools
License: https://creativecommons.org/licenses/by/4.0/

The llms.txt File Builder generates the curated, AI-readable index that an increasing number of language models look for when they read your site. Raw HTML is noisy; an llms.txt file hands AI tools a clean Markdown map of your most important pages so they cite the right things. This tool walks you through the standard’s structure and emits a valid file ready to host.

Why llms.txt matters for AI discoverability

When a user asks a language model about your product or domain, the model may retrieve and read your site. What it reads is not the rendered page the user sees — it is the underlying HTML, which is full of navigation menus, ads, cookie notices, metadata, and footer links that dilute the actual content. A model reading a page to generate an answer spends part of its attention window on noise.

An llms.txt file at your domain root gives the model a pre-curated signal: here are the five to ten most important pages, described in plain prose, with the exact URLs and a note on what each one covers. Models that follow the standard will read this file first and use it to decide which pages to fetch for deeper context. The result is more accurate citations, better answers to questions about your product, and higher recall when a user asks a model to recommend tools in your category.

How it works

The llms.txt format is plain Markdown with a fixed shape. The file opens with an H1 title (your site or product name), followed by an optional blockquote summary that states what you do in one line. After that come H2 sections — typically Docs, Guides, API, or About — each containing a bullet list of links. Each link uses Markdown syntax with an optional note after a colon, for example - [Quickstart](https://site.com/quickstart): Get running in five minutes. The builder takes your title, summary, and grouped links and renders exactly this structure, escaping nothing you do not need and dropping empty sections.

What a complete llms.txt file looks like

# Acme Docs

> Acme is an API for sending transactional email with built-in
> deliverability and analytics.

## Docs

- [Quickstart](https://acme.com/docs/quickstart): Get started in under five minutes
- [API Reference](https://acme.com/docs/api): Full REST API with request and response schemas
- [Webhooks](https://acme.com/docs/webhooks): Receive delivery and open events in real time

## Guides

- [Sending from your domain](https://acme.com/guides/custom-domain): Set up SPF, DKIM, and DMARC
- [Handling bounces](https://acme.com/guides/bounces): Suppress invalid addresses automatically

This format is what this builder produces. Serve it at https://yourdomain.com/llms.txt with Content-Type: text/plain.

Tips and example

Curate, do not dump. Link the 5–10 pages you most want an AI to read and cite, not every URL — the point is a high-signal map, not a sitemap.
Write notes for ambiguous titles. The colon note after a link is your chance to tell the model what the page actually covers when the title alone is unclear.
Serve it as text/plain at the root. Host it at /llms.txt; consider an /llms-full.txt with full page content for models that want deeper context.
Update it when your site structure changes. A stale llms.txt pointing to moved or deleted pages is worse than none — the model fetches a 404 and loses context.
The blockquote summary is the most important line. It is the one sentence a model uses to understand your product before deciding whether to read further. Make it specific and accurate.