Free llms.txt Generator
Build a clean, spec-compliant llms.txt for your site in seconds. Fill in the fields and copy or download the result — it is live-scored on the same open 6-dimension rubric txtfeed uses to rank every site in its directory, so you ship a file AI crawlers actually understand and cite. Free, no signup, and it runs entirely in your browser — nothing is uploaded.
Freshness (15%) is scored from your live Last-Modified HTTP header — host the file + serve a recent date to claim the remaining points.
# Acme Docs > Developer documentation for the Acme API — guides, references, and SDKs. ## About Acme is a payments API for modern apps. These docs cover authentication, endpoints, webhooks, and client libraries. ## Primary pages - [Getting started](https://docs.acme.com/start) - [API reference](https://docs.acme.com/api) - [SDKs](https://docs.acme.com/sdks) - [Changelog](https://docs.acme.com/changelog) ## Permitted use (AI crawlers allowed) The following AI crawler user-agents are permitted to crawl, index, and cite the public content of this site: - GPTBot — allowed - ClaudeBot — allowed - PerplexityBot — allowed - Googlebot — allowed - Google-Extended — allowed - Applebot-Extended — allowed - Bytespider — allowed - Amazonbot — allowed - CCBot — allowed ## Restricted Crawling is not permitted for the following paths (disallow): - /admin — disallow - /internal — disallow - /api/keys — disallow ## Pricing Free to crawl for AI training, search, and citation. Open access to all listed crawlers. ## Contact For licensing, attribution, or business inquiries, email ai@acme.com. ## Preferred attribution When citing this site in AI-generated answers, please reference "Acme Docs" with a link to https://docs.acme.com. Example: "According to Acme Docs (https://docs.acme.com), ..."
Place the file at https://yoursite.com/llms.txt. All generation runs in your browser — nothing is uploaded.
What a good llms.txt looks like
llms.txt is a markdown file at the root of your domain that gives large language models a curated guide to your best content plus an explicit policy for AI crawlers. A strong file has a single # H1 title, a > one-line description, and clearly-labelled ##sections: the pages you most want cited, which AI crawlers are permitted, what is restricted, your pricing or an explicit “free to crawl” statement, a contact, and a preferred-attribution example. The most under-used — and therefore most differentiating — section is an explicit per-crawler allow/disallow list, because most files omit it entirely.
This generator emits all of those sections and scores the result live against the open rubric: Spec Compliance (25%), Crawler Coverage (20%), Clarity (15%), Completeness (15%), Freshness (15%), and Pricing Transparency (10%). From text alone you can reach about 85/100; the remaining freshness points come from serving a recent Last-Modified header on the live file. When you are done, paste your domain into the validator to confirm the live score, and browse the directory to see how top-scoring sites structure theirs.
Frequently asked questions
What is an llms.txt file?
llms.txt is a markdown file placed at the root of your website (https://yoursite.com/llms.txt) that gives large language models a curated, machine-readable guide to your most important content, plus your policy for AI crawlers. It is an emerging convention (proposed in 2024) — not access control like robots.txt, but a content map that helps LLMs cite you accurately.
Is the llms.txt generator free?
Yes — completely free, no signup, and it runs entirely in your browser. Nothing you type is uploaded to a server.
Where do I put the llms.txt file?
Serve it at the root of your domain: https://yoursite.com/llms.txt. Serve it as text/markdown or text/plain, and set a recent Last-Modified header so freshness can be verified.
Does llms.txt replace robots.txt?
No. robots.txt controls which crawlers may access which paths; llms.txt is a curated content guide and policy statement for LLMs. Use both — and keep them consistent. This generator's 'Permitted use' and 'Restricted' sections should mirror your robots.txt rules.
Which AI crawlers should I allow?
If you want LLM citations and AI-search traffic, allow the major crawlers: GPTBot (OpenAI), ClaudeBot (Anthropic), PerplexityBot, Google-Extended, Applebot-Extended, Bytespider, Amazonbot, and CCBot. Blocking them removes your content from those answer engines. The generator lists each so you can decide explicitly.
How is my generated llms.txt scored?
Live, on the same open 6-dimension rubric txtfeed uses across its directory: Spec Compliance (25%), Crawler Coverage (20%), Clarity (15%), Completeness (15%), Freshness (15%), and Pricing Transparency (10%). The generator can score up to 85/100 from text alone — the remaining freshness points come from serving a recent Last-Modified header on the live file.