---
title: "llms.txt generator: build the file in your browser · DotsAgent"
description: "Generate an llms.txt file in the llmstxt.org format, with an H1 name, a blockquote summary and H2 link sections. Follows the 10 August 2026 spec revision."
url: https://dotsagent.io/agent-ready/llms-txt
---

Open your site · generator

# llms.txt generator

llms.txt is a short Markdown index that points agents at the pages worth reading. Edit the fields on the left and the file on the right updates as you type.

`/llms.txt`

```
# Acme API

> Acme API lets small online shops take card payments and send receipts over a REST API.

All endpoints use JSON over HTTPS. Amounts are integers in the smallest currency unit.

## Docs

- [Quickstart](https://example.com/docs/quickstart.md): Install and first request
- [Authentication](https://example.com/docs/auth.md): API keys and scopes
- [Webhooks](https://example.com/docs/webhooks.md): Events and retries

## API

- [OpenAPI description](https://api.example.com/v1/openapi.json): Every endpoint and schema
- [Errors](https://example.com/docs/errors.md): Error codes and what to do next

## Optional

- [Changelog](https://example.com/changelog.md)
- [Blog](https://example.com/blog.md): Product news
```

Save the output as /llms.txt at your site root, or under a subpath such as /docs/llms.txt, where the most specific file wins. Link to Markdown copies of pages (page.md or page.html.md) so an agent gets clean text instead of HTML.

## What the format requires

The only required part is an H1 with the site or project name. After it come an optional blockquote summary, optional paragraphs or lists without headings, and H2 sections that each hold a list of links written as - [name](url): notes. The August 2026 revision turned the Optional section into a convention and dropped the llms_txt2ctx tool.

## Does anyone read it?

We have no operator statement that any crawler in our bot directory fetches llms.txt, so don't expect search traffic from it. Lighthouse checks for the file, and an agent you point at it can use it like any other page. Markdown in general has thin evidence too: some coding agents ask for it, but AnswerShare saw frontier crawlers do so 0 times in 1,277,965 requests.

## Questions about llms.txt

### Where do I put llms.txt?

At the root of your site, so it is reachable at /llms.txt. The spec also allows files under subpaths such as /docs/llms.txt, and the most specific one applies to that part of the site.

### What is llms-full.txt?

It is not part of the llms.txt spec. Some sites and tools use the name, but the spec defines no format for it, so treat it as a site-specific extra rather than something agents will look for.

### Does llms.txt help SEO?

There is no evidence that it does. None of the crawler documentation we cite says the file is read, so think of it as help for agents and developer tools, not a ranking feature.

### How do agents find the Markdown version of a page?

The spec suggests the same URL with .md added, as page.md or page.html.md. A page can also announce its Markdown copy with rel="alternate" type="text/markdown" or rel="describedby", either in an HTML link element or in a Link header.

### What does the Optional section in llms.txt do?

Links under an H2 titled Optional are ones an agent may skip when it needs to save context. Since the August 2026 revision this is only a convention, so agents are free to ignore the distinction.

## Sources

1. [llmstxt.org](https://llmstxt.org/)/
2. [github.com](https://github.com/AnswerDotAI/llms-txt)/AnswerDotAI/llms-txt

Independent reference for people who build AI agents. Not affiliated with any vendor named here.

© 2026 DotsAgent · Facts checked October 1, 2026