---
language: en
title: "llms.txt"
description: "llms.txt is a proposed file containing context and links for agents. Learn its purpose and why it does not replace robots.txt, a sitemap, or the fundamentals of SEO."
canonical: "https://tropk.ai/en/resources/glossary/llms-txt"
last_modified: "2026-10-12T16:14:39.162Z"
---

# llms.txt

Reviewed on 2026-10-06.

## What it means

llms.txt is a proposed Markdown file that brings together context and links to help agents and language models find information on a website. The proposal describes a curated index, with details available at the linked destinations. It is different from an access rule and does not require all AI systems to read or use the file.

## Why it matters for marketing

For marketing, it can be useful when there is a documentation library that agents need to navigate. Its value lies in organization, accuracy, and maintenance: identifying reliable pages, explaining the scope, and avoiding instructions or claims that conflict with the website. Adoption should address a concrete need rather than serve as a substitute for accessible, well-explained content.

## Example in practice

A documentation website publishes an llms.txt file with an overview of its product and links to Markdown API references. An agent that uses this index may find the information more easily. On a commercial website, however, adding the file does not prove that [ChatGPT](/en/resources/glossary/chatgpt) or Google has started citing the brand. That effect requires independent evidence.

## How to implement or verify

If you adopt it, check the current proposal format, the links, and their consistency with the public content. Keep dates and offer information consistent, and assign someone to review the file. Test access to the file and its destinations. Report observed use by customers or agents, where applicable, without extrapolating to all platforms or to ranking changes.

## Important distinctions

llms.txt does not replace [robots.txt](/en/resources/glossary/robots-txt), which sets out [crawling](/en/resources/glossary/crawling) rules, or a [sitemap](/en/resources/glossary/sitemap), which helps URLs get discovered. Google states that it does not use these special files as a requirement for its generative Search experiences. The proposal may have applications of its own, especially for documentation, but should not be presented as a universal [GEO](/en/resources/glossary/geo) requirement or a guarantee of visibility.

## Sources and references

- [The llms.txt proposal](<https://llmstxt.org/>) — llmstxt.org
- [Optimizing your website for generative AI features on Google Search](<https://developers.google.com/search/docs/fundamentals/ai-optimization-guide>) — Google Search Central

## Continue a leitura

- [AI search](</en/resources/glossary/ai-search>)
- [Sitemap](</en/resources/glossary/sitemap>)
- [robots.txt](</en/resources/glossary/robots-txt>)

## About the author

[Vinicius Pacheco](</en/team/vinicius-pacheco>)

Responsible for Tropk’s technical content, focusing on crawling, indexing, structured data, and agent access to content.

---

[All pages in Markdown](<https://tropk.ai/sitemap.md>)