llms.txt generator
This is one of the five queries behind this directory. We sent it to a web search, kept every source the results returned, then asked a model the same question 6 times and recorded which sources it actually cited. 4 of the 10 sources were cited at least once.
What we measured
Measured 2026-10-16 · gpt-oss-20b via text.pollinations.ai (alias "openai") · read the page body · 6 of 6 runs usable for this query
llmstxtgenerator.dev
LLMs.txt Generator — Create AI-Ready Website Files for Free
llmstxtpro.com
Free LLMs.txt Generator & Validator – Free LLMs.txt
crawlreadyai.com
How to Create llms.txt (or llm.txt) Step by Step
tools.town
How to Create llms.txt — Step-by-Step Guide | Tools.Town
baike.baidu.com
llmstxt-generator - 百度百科
mobileproxy.space
llms.txt 教程：如何把你的内容交给 AI 搜索引擎
aeoagency.us
LLMs.txt Explained: What It Is, Why It Matters, and How to Set Up One
llmsfile.com
LLMs File - Free llms.txt Generator and AI Search Visibility
ai-herald.com
What Is llms.txt? The Complete Guide to the Proposed AI Web Standard
ghg365.com
llms.txt Generator - Free AI-Friendly Website Description
Titles and domains come from the pages themselves, so you can find them. The citation count, the rank, the word count and the retrieval access are our measurement, and the method is published in full.
What this query shows
The most-cited source in this pool was llmstxtgenerator.dev — named in 6 of the 6 runs we could measure.
The page that ranked #1 on entry (baike.baidu.com) was never cited once. It sat at the top of the search results and the model still went elsewhere.
The lowest-ranked source that still got cited was llmstxtgenerator.dev (#5 on entry, cited 6 of 6 times) — search position and citation are not the same thing.
6 of the 10 sources in this pool were never cited in any run. A zero here is a result we publish, not a result we hide.
1 source was cited in every single run: llmstxtgenerator.dev.
3 sources here turn away the retrieval crawlers outright — OAI-SearchBot, ChatGPT-User or PerplexityBot. That is a closed door, not a content problem, and no amount of writing fixes it.
Across the 6 runs, the set of cited sources overlapped by 0.544 on average (range 0.250–1.000). That is not settled. Who gets cited changes from run to run, which means the slot is still open — this is the kind of query worth working on.
Where this query sits
Of the 5 queries we measured, this one sits #2 on our list of the queries that are still open, ordered by how much the cited set changes between runs.
Questions this query answers
Does adding an llms.txt get a page cited?
Not by itself. llms.txt describes what a site contains so a model can read it; our measurement records which sources were actually cited, and treats llms.txt as one of the things we check on a page, not as a cause of citation. In this pool 4 of 10 sources were cited at least once.
What is a fake 200 llms.txt?
A URL that answers HTTP 200 with an HTML shell instead of the file, usually because a single-page app routes every unknown path back to its index. In our 48-source pool, 4 did exactly this. A checker that only looks at the status code will mark those as present, so you have to read the Content-Type and the first line, which should start with a heading.
How many links should an llms.txt list?
It is not a sitemap. The largest AI-facing index we compared lists 59 links against roughly 28,000 pages. Ours lists 17. What matters is that each line says what the link is, not how many lines there are.