/ llmtxt.info
Français

/llms.txt — the reference

The reference site for llms.txt

A neutral, bilingual reference covering the proposed standard helping large language models navigate websites: what it is, how it works, how to build one, and what it actually does (and does not) do today.

Start with the basics Validate a file Generate one

Bilingual EN / FR · Open source · Lire en français

llms.txt 
# llmtxt.info

> The reference site on llms.txt — what it is, how it works, how to create one, with a free validator and generator.

## Core pages

- [What is llms.txt](https://llmtxt.info/what-is-llms-txt/): definition, origin and adoption status.
- [How llms.txt works](https://llmtxt.info/how-it-works/): file structure and parsing rules.
- [How to create llms.txt](https://llmtxt.info/how-to-create/): step-by-step with templates.
- [Comparison](https://llmtxt.info/comparison/): llms.txt vs robots.txt vs sitemap.xml.

## Tools

- [Validator](https://llmtxt.info/validator/): paste a file, get diagnostics.
- [Generator](https://llmtxt.info/generator/): build a llms.txt from a form.

## Optional

- [FAQ](https://llmtxt.info/faq/): twenty common questions.
- [Glossary](https://llmtxt.info/glossary/): key terms.

What you can do here

01 / Learn

Understand the spec

What llms.txt is, what problem it solves, who proposed it, who adopted it, and what its actual status is in 2026.

What is llms.txt →

02 / Build

Create your file

Templates, step-by-step instructions and per-stack guides (Next.js, Astro, WordPress, Cloudflare Pages, Vercel, Netlify).

How to create →

03 / Verify

Validate & test

Paste your file in the validator to check spec compliance, or use the generator to scaffold a clean baseline in seconds.

Validator → Generator →

In one paragraph

llms.txt is a Markdown file placed at a website’s root (/llms.txt) that gives large language models a curated map of the most useful pages to read. It was proposed in September 2024 by Jeremy Howard at Answer.AI. It is not a W3C or IETF standard, and as of 2026 no major LLM provider has publicly committed to consistently fetching it — but it’s widely adopted by documentation platforms (Anthropic, Cloudflare, Stripe, Mintlify, Vercel, Perplexity) and useful as a stable, machine-readable contract you control on your own site.

Sources: llmstxt.org, Answer.AI announcement.

Explore the topic

Pages are organized in three clusters: foundations, builder’s guide, and reference. Pick where you want to start.

Foundations

Builder’s guide

Reference