Free tool · no key · runs on the live API
llms.txt generator and validator
Check a site's llms.txt against the format at llmstxt.org, or draft one from the site's own URLs. Edit the file here and the checks update as you type; copy or download it when it is ready.
Checks
Load a site's llms.txt, draft one, or paste a file into the editor. It is checked against the llmstxt.org format as you type.
How it works
Check fetches https://<site>/llms.txt (or the llms.txt URL you enter) through GET https://api.contextfetch.dev/r/, which returns a text file as it is. Many sites answer every path with their web app, so the tool tells an HTML page from a real file.
Draft calls POST https://api.contextfetch.dev/v1/map for up to 200 of the site's URLs, from its homepage links and the sitemaps its robots.txt names (else /sitemap.xml), and groups them by their first path segment. The validator itself runs in your browser and sends nothing anywhere.
ContextFetch's own file is at contextfetch.dev/llms.txt. The reader also uses llms.txt: for a docs site root, /r/ returns the site's llms.txt when it has one.
Questions
What is llms.txt?
A Markdown file at /llms.txt that tells AI agents what a site is and where its most useful pages are, proposed at llmstxt.org. It has an H1 with the site's name (the only required part), a one-line blockquote summary, optional details, then H2 sections that list links as - [name](url): notes. A section called Optional holds links an agent can skip when it needs less context.
What does the validator check?
Errors: an empty file, an HTML page instead of a text file, or no H1 title at the top. Warnings: no summary, headings before the first section, a second H1, section lines that are not links, links with relative URLs, and empty sections. Each comes with its line numbers.
How is the draft made?
From the site's URLs, found with ContextFetch's /v1/map endpoint in its homepage links and sitemaps: one section per top-level path with two or more pages, the rest under Pages, with link names taken from the URL. It is a start: rename the links, add notes, and keep only the pages an agent needs.
Is it free?
Yes. Checking a site's file or drafting one is one keyless request each, out of 25 a day per network. Pasting and editing a file costs nothing: the checks run in your browser.
What is llms.txt?
A Markdown file at /llms.txt that tells AI agents what a site is and where its most useful pages are, proposed at llmstxt.org. It has an H1 with the site's name (the only required part), a one-line blockquote summary, optional details, then H2 sections that list links as - [name](url): notes. A section called Optional holds links an agent can skip when it needs less context.
What does the validator check?
Errors: an empty file, an HTML page instead of a text file, or no H1 title at the top. Warnings: no summary, headings before the first section, a second H1, section lines that are not links, links with relative URLs, and empty sections. Each comes with its line numbers.
How is the draft made?
From the site's URLs, found with ContextFetch's /v1/map endpoint in its homepage links and sitemaps: one section per top-level path with two or more pages, the rest under Pages, with link names taken from the URL. It is a start: rename the links, add notes, and keep only the pages an agent needs.
Is it free?
Yes. Checking a site's file or drafting one is one keyless request each, out of 25 a day per network. Pasting and editing a file costs nothing: the checks run in your browser.
More free tools
- URL to MarkdownPaste a URL, get the clean Markdown the API returns for it.GET /r/{url}
- Token counterA page's tokens as raw HTML, as Markdown and pruned to a question.GET /r/{url}
- AI crawler checkerWhich AI crawlers a site's robots.txt blocks: GPTBot, ClaudeBot and more.GET /r/{site}/robots.txt
- AI-ready badgeA badge for your site with its AI crawler rules and llms.txt status from our crawl.
- Site mapperA site's URLs from its links and sitemaps, without fetching the pages.POST /v1/map
- Search API cost calculatorMonthly cost at list price for ContextFetch, Exa and Tavily.
Give your agent the web
Your free key comes with 2,500 credits, no signup. One credit is one search or one page read.