llms.txt is a proposed plain-text file at a site's root that lists the URLs and short descriptions a site owner wants LLMs to prioritize when summarizing that site — and as of mid-2026 no major answer engine has confirmed that it uses the file for retrieval or citation.
The proposal comes from Answer.AI and is documented at llmstxt.org. It defines a markdown-style file (/llms.txt) with a title, short description, and grouped links, plus an optional /llms-full.txt variant containing full content or excerpts. It is deliberately similar in spirit to robots.txt and sitemap.xml: a well-known path a bot might look for.
Adoption is asymmetric. Publishers ship the file readily; the answer engines — ChatGPT, Perplexity, Google AI Overviews, Gemini, Claude — have not publicly documented consuming it. That may change, and there is no downside to publishing one: it is cheap, machine-readable, and gives a clean summary if any crawler does start reading it.
Practical guidance: ship llms.txt pointing at your best pages, ship llms-full.txt with short excerpts (not full text — that hands scrapers a bulk copy kit), and do not treat either file as a substitute for the things that do demonstrably work — server-rendered HTML, QAPage markup, and IndexNow discovery.
If an engine announces that it consumes llms.txt, publishers who already ship it get a free head start. If none do, the file is harmless — it costs nothing and gives human reviewers a useful summary of what the site claims to cover.