What is llms.txt?
llms.txt is a plain-text file at the root of a website that gives large language models a curated, Markdown-formatted map of the site's most useful content. It was proposed by Jeremy Howard in 2024 and is a convention, not a standard: no model is obliged to read it.
What the file contains
The file is Markdown: an H1 with the site or product name, a short summary, then lists of links with one-line descriptions of what each page covers. Many sites also publish an llms-full.txt containing the full text of those pages, so an assistant can retrieve the whole corpus in a single fetch.
It is complementary to robots.txt and sitemap.xml rather than a replacement. robots.txt states who may crawl, sitemap.xml lists every URL, and llms.txt states which pages are worth reading and what they say.
Why sites publish one
HTML pages carry navigation, scripts, and styling that waste an assistant's context window and obscure the content. A Markdown index — and Markdown versions of the pages themselves — gives a model the substance without the markup, which makes accurate quoting and citation more likely.
Changebot publishes both files: llms.txt as the index and llms-full.txt as the full corpus, alongside a Markdown twin of every content page.
