llms.txt Generator
Free llms.txt generator. Enter a site URL or paste pages, and get llms.txt and llms-full.txt files that help AI crawlers understand your site.
# Acme Widgets Docs > Developer documentation for the Acme Widgets REST API and SDKs. Acme Widgets lets teams embed configurable widgets in any web page. The API is JSON over HTTPS; SDKs exist for JavaScript and Python. ## Docs - [Quickstart](https://docs.example.com/quickstart): Install the SDK and render a first widget in five minutes - [API reference](https://docs.example.com/api): Every endpoint with request and response examples ## Optional - [Blog](https://example.com/blog): Release announcements and tutorials
What Is an llms.txt Generator?
An llms.txt generator is a tool that writes the /llms.txt file for a website: a short markdown document that tells large language models what the site is about and which pages to read. The format, proposed at llmstxt.org, is deliberately simple so it can be produced by hand or by a script. It starts with an H1 naming the site, a blockquote with a one-sentence summary, optional paragraphs of context, and then H2 sections that list links in the form - [title](url): description. A section called Optional marks pages a model may skip.
This generator works two ways. From URL crawls your sitemap and reads page titles and meta descriptions through a small server route. Manual lets you type or edit every line in the browser. Both produce llms.txt and the longer llms-full.txt.
How to Create an llms.txt File
- Open From URL, enter your site address and click Fetch pages. The tool reads sitemap.xml or the homepage links and collects titles and descriptions for up to 40 pages.
- Switch to Manual to rename the site, tighten the summary and fix any description that came through empty.
- Group links into sections such as Docs, Guides, API and Optional. Add a section for pages the crawl missed.
- Copy or download llms.txt, and llms-full.txt if you want the expanded version.
- Publish both at the root of your domain, alongside robots.txt and sitemap.xml.
The llms txt Format at a Glance
Each element of the file has a fixed meaning for the reader:
| Element | Markdown | Required |
|---|---|---|
| Site name | # Acme Docs | Yes, exactly one H1 |
| Summary | > One sentence about the site | Recommended |
| Details | Plain paragraphs, no headings | Optional |
| Section | ## Docs | At least one |
| Link | - [Quickstart](https://…/quickstart): Install and run | One per page |
| Skippable pages | ## Optional | Optional |
Keep descriptions to one clause. The file is meant to fit in a model's context window next to the user's question, so brevity matters more than completeness; that is what llms-full.txt is for.
llms.txt Example for a Documentation Site
The sample loaded in the tool renders to this llms.txt example:
# Acme Widgets Docs > Developer documentation for the Acme Widgets REST API and SDKs. Acme Widgets lets teams embed configurable widgets in any web page. ## Docs - [Quickstart](https://docs.example.com/quickstart): Install the SDK and render a first widget - [API reference](https://docs.example.com/api): Every endpoint with request and response examples ## Optional - [Blog](https://example.com/blog): Release announcements and tutorials
Why Use an llms.txt Generator
An llms.txt generator saves the tedious part: collecting every important URL with an accurate one-line description. Sites that publish the file give ChatGPT, Claude, Perplexity and coding assistants a curated map instead of whatever a crawler happens to index, which leads to answers that cite the right page. Regenerate the file when you add sections to your docs, and keep the meta tag generator handy: the same titles and descriptions feed both your search snippets and your llms.txt.
Frequently Asked Questions
What is llms.txt?
llms.txt is a markdown file served at the root of a website that tells large language models what the site is and which pages matter. It was proposed at llmstxt.org in 2024 and follows a fixed shape: an H1 with the site name, a blockquote summary, optional prose, then H2 sections containing link lists. AI crawlers and coding assistants read it instead of guessing from navigation menus.
How does the llms.txt generator build the file from a URL?
It fetches your /sitemap.xml, follows one level of sitemap index, and collects up to 200 URLs; when there is no sitemap it uses the links on the homepage. It then fetches the title and meta description of up to 40 pages and writes them as a link list. Titles and descriptions come from your own pages, so improve those and the file improves.
What is the difference between llms.txt and llms-full.txt?
llms.txt is the short index: one line per page with a link and description. llms-full.txt expands every entry into its own heading with the URL and description underneath, so a model can load one file and get the whole overview without following links. Sites with long documentation often put the full page contents in llms-full.txt.
Can you show an llms.txt example?
The sample loaded in the Manual tab is a complete llms.txt example: a site name, a one-line summary in a blockquote, a Docs section with two links, and an Optional section for secondary pages. Sections named Optional signal to the model that those links can be skipped when context is limited.
Where do I put the files?
Serve them as plain text or markdown at https://yoursite.com/llms.txt and /llms-full.txt. On Next.js, drop them in public/; on Hugo or Jekyll, in static/. Link the file from robots.txt or your docs home if you want crawlers to find it quickly.
Is the crawl private?
The URL mode uses a small server route because browsers cannot fetch other domains. It only reads public pages, fetches at most 40 of them with an 8 second timeout each, and does not store anything. The Manual mode never leaves your browser.