Free llms.txt generator.
ChatGPT, Claude and Perplexity are already describing your site to potential customers. An llms.txt file is how you hand them the right summary instead of hoping they guess. Fill in the form, get a spec-correct file, drop it at your site root. No signup, nothing stored.
Becomes the blockquote under the title. One sentence, plain language.
# Your site
Save this as llms.txt at your site root, e.g. https://yoursite.com/llms.txt.
What is llms.txt?
llms.txt is a markdown file that lives at your site root, next to robots.txt. Proposed by Jeremy Howard of Answer.AI in late 2024, it gives language models a curated, token-cheap version of your site: a title, a one-line summary in a blockquote, and sections of links to the pages that actually matter.
The problem it solves is real. AI assistants work with limited context windows, and your site is a soup of navigation, cookie banners and footers. When someone asks an assistant “what does your product do” or “what does an agency like this charge”, the model reconstructs an answer from whatever it managed to parse. llms.txt replaces that guesswork with your own words.
A complete llms.txt example.
Here is a realistic example for a small SaaS. The format is the whole spec: one H1, one blockquote summary, optional prose, then H2 sections of markdown links with optional notes. A final section named “Optional” marks links a model can skip when short on context.
# Acme Analytics > Self-serve product analytics for small SaaS teams. Free tier, 5-minute setup, EU hosting. Acme tracks events, funnels and retention without a data team. Pricing is flat per project, not per seat. ## Docs - [Quickstart](https://acme.com/docs/quickstart): install the snippet and see events in 5 minutes - [API reference](https://acme.com/docs/api): REST + SDKs for JS, Python, Ruby ## Key pages - [Pricing](https://acme.com/pricing) - [Acme vs Mixpanel](https://acme.com/compare/mixpanel) ## Optional - [Changelog](https://acme.com/changelog)
You can see a live one at techpotions.com/llms.txt. This site publishes the same file this generator produces.
How to create and ship llms.txt.
One: fill in the generator above. Give it a name, a one-line summary, and your 5 to 15 most load-bearing pages, grouped into sections. Two: download the file. Three: put it at your site root so it resolves at /llms.txt. On static hosting that means dropping the file into your public folder; in Next.js or similar frameworks, add a small route that returns the text. Four: reference it from your sitemap or docs if you like, and update it when your key pages change.
Keep it honest and short. The file is for machines summarizing you to humans, so plain claims beat marketing language, and 20 well-chosen links beat 200.
Want to block AI crawlers instead?
llms.txt invites AI in; robots.txt is where you set limits. Each AI company crawls with a named user agent, so you can allow the assistants that cite you and refuse the bulk scrapers. The names that matter in 2026: GPTBot, OAI-SearchBot and ChatGPT-User (OpenAI), ClaudeBot (Anthropic), Google-Extended (Google AI training opt-out), PerplexityBot, CCBot (Common Crawl) and Bytespider (ByteDance).
# Allow AI assistants that cite and send traffic User-agent: GPTBot Allow: / User-agent: ClaudeBot Allow: / User-agent: PerplexityBot Allow: / # Opt out of Google AI training (search crawling unaffected) User-agent: Google-Extended Disallow: / # Block bulk scrapers you get nothing from User-agent: CCBot Disallow: / User-agent: Bytespider Disallow: /
A word of caution before you block everything: assistants increasingly answer buying questions, and a site they cannot read is a site they cannot recommend.
Common questions.
01What is llms.txt?
llms.txt is a plain-markdown file at your site root that tells AI assistants what your site is and which pages matter. It was proposed by Jeremy Howard of Answer.AI in late 2024 as a curated, token-friendly alternative to making language models parse your whole site. Think of it as robots.txt’s helpful sibling: robots.txt says what crawlers may not do, llms.txt says what they should read.
02Do AI companies actually read llms.txt?
Adoption is real but uneven. Documentation platforms like Mintlify generate it automatically, and thousands of developer-facing sites publish one, but no major AI lab has committed to always fetching it. It costs a few minutes and a few kilobytes, ranks among the cheapest AI-visibility bets you can make, and the sites that publish one are consistently easier for assistants to summarize correctly.
03Where do I put the llms.txt file?
At the root of your domain, next to robots.txt: https://yoursite.com/llms.txt. It must be served as plain text or markdown. If your site is a framework app rather than static files, add a route that returns the file content, the same way you would for robots.txt.
04What is the difference between llms.txt and llms-full.txt?
llms.txt is the short index: title, summary, and curated links. llms-full.txt is an optional companion that inlines the full content of your key pages into one large markdown file, so a model can read everything in a single fetch. Start with llms.txt; add llms-full.txt if your docs are the product.
05Does llms.txt affect my Google rankings?
Not directly. Google has said it does not use llms.txt for ranking, and it is not a search engine standard. Its value is in how AI assistants, answer engines, and agents represent you when users ask about your product, which is a growing share of how people discover software.
06How is this different from blocking AI crawlers in robots.txt?
Opposite direction. robots.txt rules for agents like GPTBot or ClaudeBot control whether AI companies may crawl you at all. llms.txt assumes you want to be understood and gives the models a clean summary. Many sites sensibly do both: allow the assistants that send them traffic, and publish an llms.txt so those assistants get the story right.
- App development cost calculatorScope a web or mobile app and get an honest 2026 cost and timeline range.
- AI receptionist cost calculatorCompare an AI receptionist against in-house staff and answering services, in dollars.
- LLM API pricing calculatorCompare Claude, GPT, Gemini and DeepSeek token costs on your real usage.
Want your product to show up well in AI answers?
llms.txt is one piece. We build sites and AI products that assistants can actually read, cite and recommend: schema, GEO, and the engineering underneath. techpotions is a small studio; you talk to the people who build.