Free tool llms.txt generator for your site
llms.txt is a proposed Markdown file at the root of a site that tells language models and AI tools what the site is and which pages matter. Fill in a few fields, or paste your sitemap, and download a file in the exact format of the proposal.
- llmstxt.org format
- Copy or download
- Runs locally
Describe the site, list the pages
The sample is a help desk SaaS. Replace each field; the file and the checks update as you type. To start from a sitemap, paste the XML into the links box and press “Convert sitemap”.
Becomes the H1, the only required part of the file.
Used to turn paths such as /pricing into full URLs.
Becomes the blockquote. Say what the site is and who it is for, in one sentence.
A short paragraph or list with anything a model should know first. No headings.
One per line: Title | URL | note. Start a section with ## Name. Bare URLs and - [Title](URL): note also work, or paste a sitemap.xml.
Same format. Written under ## Optional: pages a tool can skip when it needs a shorter context.
Sections
3
H2 sections with at least one link.
Links
5
All links, Optional included.
# Brightdesk
> Help desk software for small teams: a shared inbox, live chat and a knowledge base in one app.
Brightdesk is used by support teams of 2 to 50 agents. Every plan includes the REST API and webhooks.
## Docs
- [Quick start](https://brightdesk.example/docs/quick-start): Install the widget and answer a first chat
- [API reference](https://brightdesk.example/docs/api): REST endpoints, authentication and rate limits
## Product
- [Pricing](https://brightdesk.example/pricing): Plans, limits and what each includes
- [Changelog](https://brightdesk.example/changelog)
## Optional
- [Blog](https://brightdesk.example/blog): Product news and support guides
Save as llms.txt at the root of the site: https://www.example.com/llms.txt.
Checks
- OKThe file follows the llmstxt.org format.
Share these inputs: the values go after the # in the link, so they never reach a server.
https://tapcub.com/tools/llms-txt-generator
Version v1.0Updated Update history
What each part of the file is for
The proposal defines a fixed order. The generator writes it the same way every time.
H1: the name
The first line, # Brightdesk. It is the only required element; a file without it is not an llms.txt under the proposal.
Blockquote: the summary
One line starting with >. Write it for a reader with no context: what the site is, who it serves, what is unique.
H2 sections: the file lists
Each ## Section holds a Markdown list of links in the form - [Title](URL): note. The note is optional but helps a model decide which page to open.
Optional: the skippable part
Links under ## Optional are, by convention, the ones a tool can drop when it needs a shorter context. Put archives, blogs and secondary pages here.
Two numbers sit above the file: sections with at least one link, and links in total. Empty sections are left out rather than written as empty headings.
Four steps
A first version takes a few minutes; the curation is what takes thought.
-
1
Name and summary
Type the site name and one sentence that describes it. Add a short details paragraph if a model needs context first, such as who your customers are.
-
2
List the pages that matter
Type lines as Title | URL | note, or paste your sitemap.xml and press Convert. Then delete what does not help: tag pages, paginated lists, legal boilerplate.
-
3
Move secondary pages to Optional
Blogs, archives and long references go in the Optional box so tools can skip them.
-
4
Download and publish
Upload as llms.txt to the site root, open it in a browser to confirm it is served as text, then check it with the llms.txt validator.
What the llms.txt proposal specifies
llms.txt was proposed by Jeremy Howard in September 2024 at llmstxt.org. It is a proposal, not a standard, and no major AI company has publicly confirmed that its crawlers or assistants read it. Google has said it is not needed for Google Search.
- Location:
/llms.txtat the site root (a subpath is allowed); plain Markdown - Order: H1 name (required) → blockquote summary → any non-heading Markdown → H2 sections of link lists
- Links:
- [name](url), optionally followed by: notes - The proposal also suggests serving clean Markdown versions of pages at the same URL plus
.md; this generator does not create those
| llms.txt | robots.txt | |
|---|---|---|
| Purpose | Points AI tools to the pages that explain your site | Tells crawlers which paths not to fetch |
| Status | Community proposal (2024) | IETF standard, RFC 9309 (2022) |
| Format | Markdown | Plain-text field: value lines |
| Read by | Unconfirmed for major AI crawlers; used by some coding assistants and doc tools | Google, Bing, Baidu and the major AI crawlers |
| Controls access? | No | No, it is a request |
From sitemap to llms.txt
A sitemap lists everything; llms.txt lists what explains the site. Here is how five sitemap URLs from the sample site end up.
| Sitemap URL | After Convert | Final decision |
|---|---|---|
/docs/quick-start | ## Docs · Quick start | Kept, with a note |
/docs/api | ## Docs · Api | Kept, title fixed to “API reference” |
/pricing | ## Pages · Pricing | Moved to a Product section |
/blog/2026/10/release-notes | ## Blog · Release notes | Moved to Optional |
/tag/chat | ## Tag · Chat | Deleted: no value as context |
Convert takes titles from the last part of each URL and groups pages by their first folder. That gives a draft, not a finished file: rename titles, add notes and cut pages that do not help someone understand the site.
What weakens an llms.txt
The format is simple. The content is where files go wrong.
Dumping the whole sitemap
Thousands of links defeat the purpose. A model gets more from 20 well-described pages than from every URL you have.
Relative or broken URLs
Read outside the site, /pricing has no host. Use full URLs and check that each one returns 200.
Treating it as an opt-out
llms.txt does not block anything. To keep AI crawlers away, use robots.txt; to keep content private, use a login.
Expecting a ranking boost
There is no public evidence that AI search engines rank or cite sites more because of llms.txt. Treat it as cheap, optional documentation.
See which AI crawlers come, and what they read
Whether any crawler fetches your llms.txt is a question your traffic can answer. TapCub records AI crawlers separately from people.
AI crawler report
GPTBot, ClaudeBot, PerplexityBot and other AI crawlers identified by name and behaviour, apart from human visits.
Learn moreCrawl compliance
Your robots.txt and llms.txt are fetched daily and compared with what actually crawled you.
Learn moreAI referrals
Visits that arrive from ChatGPT, Perplexity and other assistants show up as their own sources.
Learn morellms.txt generator questions
Still have a question?
Chat with the team behind TapCub — we usually reply within a few hours on business days.
What is llms.txt?
A Markdown file at /llms.txt that gives language models a short overview of a site and links to its key pages. It was proposed at llmstxt.org in September 2024. It is a proposal, not an adopted standard.
Do ChatGPT, Claude or Google read llms.txt?
Not as far as anyone has confirmed. OpenAI’s and Anthropic’s crawler documentation covers robots.txt and does not mention llms.txt, and Google has said llms.txt is not needed for Google Search. Some coding assistants and documentation tools do fetch it when pointed at a site.
Is llms.txt worth adding, then?
It is cheap: one small file, no effect on search engines. It is most useful for developer docs and products people ask AI tools about. Do not expect traffic from it, and do not skip robots.txt or a sitemap because of it.
What is the difference between llms.txt and llms-full.txt?
llms.txt is the index with links. llms-full.txt is a convention used by some documentation platforms that puts the full text of the docs into one file. The llmstxt.org page itself defines only llms.txt and the .md page versions.
Can I generate llms.txt from my sitemap?
Yes. Paste the sitemap.xml into the links box and press “Convert sitemap”. Pages are grouped by their first folder with titles taken from the URL. Then edit: rename, add notes and remove pages that add no context.
Where do I put the file?
At the site root, so it opens at https://www.example.com/llms.txt, served as plain text. The proposal allows a subpath too, for example for one product’s docs.
Does llms.txt replace robots.txt?
No. robots.txt tells crawlers what not to fetch and is followed by search engines and major AI crawlers. llms.txt is a guide to your content and controls nothing.
Update history
New features, fixes and data refreshes for this tool, newest first.
-
· v1.0
LaunchedFirst release.
Missing something or found an error? Tell us — requests that come up often go into the next update. All tool updates
Find out whether AI crawlers fetch it
Add TapCub and the bot report shows which AI crawlers visit, which pages they load and whether visits come back from AI assistants.