/terms/llms-txt

LLMS.txt

LLMS.txt is a proposed text file at the root of a website, written in Markdown, that provides a curated, AI-readable summary of the site's most important resources for large language models — an emerging companion to robots.txt and sitemap.xml.

Citation status

ChatGPTPerplexityClaudeCopilot

Last checked 2026-05-21

What is LLMS.txt?

A community proposal by Jeremy Howard of Answer.AI, introduced in September 2024. The file lives at https://example.com/llms.txt and contains: site title, a one-paragraph description, then a Markdown list of canonical resources organized by topic. The intent is to give LLMs a curated, low-friction entry point to a site — rather than expecting them to crawl an entire sitemap and infer relevance.

Status in 2026

Standardization-stage proposal. No major AI engine has officially announced support, but ChatGPT, Perplexity, and Claude have all been observed consulting llms.txt files when present. Anthropic's Claude has the most documented support among the major models. Adoption among AI-search-conscious sites is growing month-over-month, particularly in technical documentation and reference resources.

How it relates to other concepts

FAQ

Is LLMS.txt an official standard?
No. It is a community proposal, not a binding standard yet. No major AI engine has officially confirmed support. Adopting it has no downside — engines that don't support it ignore the file, and the cost to author is minimal.
What goes in LLMS.txt?
Site name, a one-paragraph description, then Markdown sections with links to canonical resources organized by topic. Keep it concise — the file is meant to be readable in a single screen by both humans and AI models.
Does LLMS.txt replace sitemap.xml?
No. Sitemap.xml is for search-engine indexing and lists every URL on your site. LLMS.txt is curated AI guidance — a hand-selected, topically-organized subset. Sites concerned with AI-search visibility should ship both.

Sources & further reading