llms.txt Generator
Describe your site, add your key pages, and get a spec-compliant llms.txt file to copy-paste. Runs entirely in your browser — nothing is uploaded.
Generated llms.txt
# Your Site Name > One-sentence summary of what your site or product does. ## Docs - [Page title](https://example.com/page): What this page covers ## Optional - [Page title](https://example.com/page): What this page covers
Save this as llms.txt and serve it from your domain root: yoursite.com/llms.txt. Plain text (UTF-8), same place robots.txt lives.
The format is markdown by design: one H1 (required), a blockquote summary, then H2 sections of links. Keep it curated — your best pages, not your whole sitemap.
What llms.txt Is (and Isn't)
llms.txt is a proposed convention from Jeremy Howard (Answer.AI), published at llmstxt.org in September 2024. The idea: context windows are finite and HTML is noisy, so give language models a small markdown file that says what your site is and links the pages worth reading — a table of contents written for machines.
The format has exactly four ingredients, in order:
- An H1 with your site or project name — the only required element
- A blockquote one-sentence summary
- Optional free-form paragraphs of context
- H2 sections of link lists:
- [title](url): description. A section named "Optional" marks links that can be skipped when context is tight.
What it isn't: an access-control file (that's robots.txt), a ranking hack, or an official standard any AI vendor has committed to. Treat it as cheap, honest machine-readable documentation — useful to the growing set of agents and AI dev tools that do read it, harmless to everyone else. It complements the access side of GEO: robots.txt and your firewall decide whether AI can read you; llms.txt helps decide what they read first.
Frequently Asked Questions
What is llms.txt?
llms.txt is a proposed standard (llmstxt.org, introduced by Jeremy Howard of Answer.AI in September 2024) for a markdown file at your domain root that gives language models a curated index of your site: what it is, and where the pages that matter are. The format is deliberately simple — one H1 with your site name, a blockquote summary, and H2 sections listing links with short descriptions.
Do ChatGPT, Claude, or Perplexity actually read llms.txt?
Honestly: no major AI vendor has officially committed to fetching llms.txt the way search engines commit to robots.txt. Adoption is real on the publishing side — thousands of sites including major dev-tool companies serve one — and some AI coding tools and agents do fetch them. It's a low-cost bet: a few minutes of work for a file that makes your site easier for any LLM-based tool to navigate, with no downside if a given crawler ignores it.
What's the difference between llms.txt and robots.txt?
Opposite jobs. robots.txt controls access — which crawlers may fetch which paths. llms.txt curates content — it tells a model which pages are the good ones and what they cover. robots.txt is enforcement-adjacent and widely respected; llms.txt is purely informational. A site can (and typically should) have both.
What is llms-full.txt?
A companion convention: while llms.txt is an index of links, llms-full.txt inlines the actual content of those pages into one large markdown file, so a model can ingest everything in a single fetch. It's mostly used by documentation sites. Start with llms.txt; add llms-full.txt if your docs are the product.
Where do I put the llms.txt file?
At your domain root, served as plain text: yoursite.com/llms.txt — the same place robots.txt lives. On most stacks that means dropping the file into your static/public directory. Serve it with a text/plain or text/markdown content type. You can check ours at botview.app/llms.txt.
What should I include — and leave out?
Include the pages a model would need to answer questions about you: what the product does, pricing, docs, key guides. Leave out login pages, legal boilerplate, and thin tag/archive pages. The spec's spirit is curation: a short, high-signal list beats a sitemap dump. Use the Optional section for links that are useful but skippable when context is tight.
Related
- AI robots.txt generator — The access-control side
- What is GEO? — Generative Engine Optimization explained
- How to appear in AI search — The full playbook
- Check all 18 AI crawlers at once — Verify AI can actually reach you
llms.txt Done. Can AI Crawlers Even Reach You?
A perfect llms.txt is worthless behind a firewall 403. Scan your site to verify all 18 AI crawlers get through.
Scan Your Site FreeNo signup needed