# llms.txt *A proposed index file for language models* An `llms.txt` is a Markdown file at the root of a site that lists its important pages with a sentence about each, meant to be read by language models rather than by browsers. It is a community proposal, not a standard any crawler has committed to. **Canonical:** https://spoko.space/glossary/llms-txt/ **Language:** en **Category:** SEO and AI search **Also known as:** llms-full.txt, LLM index **Published:** 2026-09-22 **Glossary:** https://spoko.space/glossary/ --- ## What it is {#what-it-is} One Markdown file, at `/llms.txt`, listing the pages of a site that are worth reading, each with a line saying what it holds. Optionally a second file, `llms-full.txt`, with much more of the content inline. The idea comes from the same place as `robots.txt`: a model asked about your company has a limited budget of pages it can fetch, and HTML is an expensive way to spend it — navigation, scripts, markup, cookie banners, and the answer somewhere in the middle. A curated index of plain text is cheaper to read and easier to quote. ## How honest to be about it {#how-honest-to-be-about-it} Completely, because this is the part most articles about `llms.txt` skip: **no major AI crawler has committed to reading it.** It is a proposal with real momentum and no guarantee behind it. Anyone telling you it will get your site into ChatGPT's answers is selling something. What makes it worth doing anyway is the cost. On this site the four files — English and Polish, short and full — are generated from the content collections at build time. Nobody writes them, nobody updates them, and a new post or a new page appears in the right one automatically. A build gate fails if a page in the sitemap is not linked from the index of its language. That is a rounding error of effort against an upside that might arrive. If it had to be maintained by hand, my answer would be different. ## What goes in it {#what-goes-in-it} The index is only useful if what it points at is also cheap to read, which is why the two go together here: every page the sitemap lists ships a plain-Markdown twin at the same address with a `.md` suffix, and every line of `llms.txt` names it. The headings in those files carry the same anchors as the HTML page, so a model that quotes one section can cite a URL that resolves for a human reader too. Each language gets its own complete index, linking only its own pages and pointing at the other. One bilingual file would have made both halves harder to read and neither complete. ## What llms.txt is not {#what-llmstxt-is-not} It is not a ranking signal, it is not read by Google Search, and it does not replace either the sitemap or the structured data. It is also not a place for marketing copy: the file exists so a machine can find the sentence that answers a question, and padding it with adjectives makes it worse at exactly that. ## Related terms {#related-terms} - [AEO](https://spoko.space/glossary/aeo/): AEO is the work of making a page usable as a source by systems that answer questions directly — AI assistants and AI overviews — rather than only listing links. The goal shifts from being clicked to being quoted correctly and attributed. — Markdown: https://spoko.space/glossary/aeo.md - [structured data](https://spoko.space/glossary/structured-data/): Structured data is a block of machine-readable facts added to a page — what it is, who wrote it, what it costs — using the schema.org vocabulary, usually as JSON-LD. Search engines read it to understand the page and sometimes to decorate the result. — Markdown: https://spoko.space/glossary/structured-data.md - [canonical URL](https://spoko.space/glossary/canonical-url/): A canonical URL is the address a page names as the real one for its content, so a search engine that reaches it by any other route indexes the named version instead. It is a strong hint, not an instruction, and Google can overrule it. — Markdown: https://spoko.space/glossary/canonical-url.md - [Google Search Console](https://spoko.space/glossary/google-search-console/): Search Console is the free tool where Google reports what it knows about your site: which queries showed it, where it ranked, which pages are indexed and which are not, and what its crawler found wrong. It is the only first-party source for any of it. — Markdown: https://spoko.space/glossary/google-search-console.md ## Where I write about this {#related-posts} - [Parts & Accessories Catalog](https://spoko.space/vw-polo-6r-parts-catalog/) — Markdown: https://spoko.space/vw-polo-6r-parts-catalog.md Headless CMS parts catalog for VW Polo 6R. Astro SSG, Vue 3, Laravel API, Filament admin, AI descriptions, DeepL translations and Cloudflare R2 image pipeline. - [AEO — How to Optimize Your Website for AI and Answer Engines](https://spoko.space/blog/aeo-answer-engine-optimization/) — Markdown: https://spoko.space/blog/aeo-answer-engine-optimization.md Answer Engine Optimization, llms.txt, islands architecture, and speed as conversion currency. A practical guide to optimizing websites for language models and generative search. ## See also {#see-also} - [AI visibility audit](https://spoko.space/ai-search-audit/) ## Sources {#sources} - [The /llms.txt file](https://llmstxt.org/) — The proposal itself: the format, the reasoning and the optional `llms-full.txt`.