llms.txt Generator
Build a valid llms.txt file for your site in the browser — no install, nothing saved on our end.
Generate your llms.txt
Paste your site's URL to auto-fill the fields below from its title, meta description, and nav links — then edit anything that needs adjusting.
Key pages
Output
# Your Site Name
How it works
This tool follows the emerging llms.txt convention: an H1 with your site name, an optional one-line blockquote summary, then Markdown link lists grouped under H2 sections. The output is assembled entirely client-side from the fields below. Auto-fill is the one part that leaves your browser: it sends the URL you enter to Draftbase's server, which reads that page's title, meta description, and nav links to pre-fill the form — nothing is stored beyond handling that one request.
Draftbase's own /llms.txt is generated the same way, from the site's real route list, as a live example of the format.
What is llms.txt and why generate one
llms.txt (some write it llm.txt — the file itself is always named llms.txt) exists because an LLM reading your site during a chat can’t click around a nav menu the way a person can. A curated Markdown link list at your domain root gives it a flat, one-pass map of what matters instead of forcing it to guess from a sitemap built for crawlers, not readers.
Adding llms.txt to Shopify, WordPress, and Docusaurus
None of these platforms serve arbitrary root-level files through their normal content editor, so the file has to land outside it: on Shopify, upload it as a theme asset and add a route via app.txt proxying or an edge redirect; on self-hosted WordPress, drop it straight into the site’s public / directory over FTP or your host’s file manager; on Docusaurus, anything placed in static/ is served from the site root unchanged, so static/llms.txt is all it takes.
Validating your llms.txt file
There’s no formal spec compliance checker yet — the convention is young enough that “valid” mostly means: served as plain text at exactly /llms.txt, starting with a single H1, and using standard Markdown link syntax throughout. Open the raw file in a browser and confirm those three things by eye; that catches the mistakes that actually break parsing. The link-text descriptions you write here serve the same job as good alt text: a short, specific line a non-visual reader relies on instead of context it can’t see.
Stop maintaining llms.txt by hand
Every entry you publish through Draftbase is available over a typed delivery API, so a script that rebuilds llms.txt from your real content — instead of a form you fill in by hand — is a small build, not a rewrite.
Hobby is free, no card. Startup is $49/mo when you outgrow it. The price is on the pricing page, where prices go.
No migration quarter, no kickoff workshop. Define a template and ship something today.
Frequently asked questions
What is llms.txt?
llms.txt is a proposed convention — a plain Markdown file at a site’s root, /llms.txt — that lists a site’s most important pages in a format built for an LLM to read in one pass, the same way robots.txt is built for crawlers rather than browsers.
Where do I put the generated file?
Save it as llms.txt and serve it at the root of your domain, e.g. https://example.com/llms.txt, alongside your existing robots.txt and sitemap.xml.
Does llms.txt improve my search rankings?
No major search engine or LLM provider has confirmed llms.txt affects ranking or citation directly. It’s a low-cost, low-risk addition — worth having, not a substitute for actual content quality or structured data.
Do I need to regenerate it every time I add a page?
For a small, mostly-static site, yes, manually. For a CMS-driven site, this is exactly what should be automated from your content, not maintained by hand.
How do I create a robots.txt file?
It's a plain text file at your domain root (e.g. example.com/robots.txt) with User-agent and Disallow/Allow lines telling crawlers what to skip. Most frameworks generate it from a route or config file rather than a static file you hand-edit — Next.js, for instance, supports an app/robots.ts that exports the rules. llms.txt follows the same root-level convention, aimed at LLMs instead of crawlers.
More free tools on the tools page, or read the mcp guide on /mcp.