What is llms.txt and how do you create one?
llms.txt is a plain-text file placed at the root of your website (yourdomain.com/llms.txt) that describes, in markdown, what your site is and which pages matter most — written for AI language models rather than human visitors. It's the AI-era counterpart of robots.txt: robots.txt restricts crawlers, llms.txt explains your site to them.
Last updated: ·7 min read
Why llms.txt exists
The idea was proposed as an open convention in 2024: language models work with limited context windows, and a typical website — menus, cookie banners, scripts — is noisy input. llms.txt hands the model a clean, curated summary instead: who you are, what you offer, where the authoritative pages live. When an AI system decides what to say about your brand, you'd rather it read your own one-page summary than reconstruct you from fragments.
Honest note: llms.txt is a convention, not a guarantee. No major AI vendor formally commits to reading it. The case for it is asymmetric risk: near-zero cost, no downside, growing adoption — and it doubles as a quality summary for any retrieval system.
The format, with a working example
The structure is deliberately simple markdown: one H1 with the brand name, a blockquote summary, then H2 sections containing annotated links.
# Acme Software
> Acme is a SaaS platform for SMB accounting automation.
> Trusted by 4,000+ businesses since 2019. HQ: Istanbul.
## Products
- [Acme Invoice](https://acme.com/invoice): E-invoicing and tracking
- [Acme Payroll](https://acme.com/payroll): Automated payroll
## Key Pages
- [Pricing](https://acme.com/pricing): Current plans and prices
- [FAQ](https://acme.com/faq): Top 20 questions answered
## Contact
- Email: support@acme.comA companion file, llms-full.txt, can carry the expanded version — full docs or long-form content — for models that want more than the map.
llms.txt vs robots.txt vs sitemap.xml
| File | Audience | Purpose |
|---|---|---|
| llms.txt | AI language models | Explain what the site is; curate key pages |
| robots.txt | Crawlers/bots | Restrict what may be accessed |
| sitemap.xml | Search engines | Enumerate every indexable URL |
How to create llms.txt in 4 steps
Write the header
Start with a single H1 (# Brand Name) followed by a short blockquote (>) that describes in 1-3 sentences what your business is, who it serves and what makes it distinct. This blockquote is the most important part — it's the summary a model will reuse.
List your key pages in sections
Group links under H2 headings (## Products, ## Docs, ## Pricing). Each line: a markdown link plus a one-line description after a colon. Only include pages that genuinely matter — this is a curated map, not a sitemap dump.
Upload to your site root
Save as plain UTF-8 text and serve it at /llms.txt (optionally a longer /llms-full.txt). Verify it opens in a browser without a 404 and isn't blocked by robots.txt.
Keep it in sync
Update the file when products, prices or positioning change. A stale llms.txt that contradicts your site is worse than none — AI systems cross-check sources against each other.
Or generate it — from verified data
Hand-written llms.txt files drift out of date and quietly contradict your site. SOV Tracker's fix layer takes the opposite approach: you verify your business facts once (name, offering, prices, FAQs) in the Verified AI Business Card, and the platform generates both llms.txt and schema.org JSON-LD from that single source — regenerated whenever the data changes.
Generate my llms.txt freeDoes your site have llms.txt? Check in 60 seconds
Fill in the website field below — the Site Readiness half of your scorecard explicitly checks llms.txt and schema.org, alongside your visibility on 5 AI engines.
Frequently asked questions
Is llms.txt mandatory?
No. It's a community-proposed convention, not an official requirement of any AI vendor. But the cost of adding one is near zero and the downside is none — which is why adoption keeps growing. Think of it as low-cost insurance for how AI systems read your site.
Where exactly does the file go?
At the root of your domain: https://yourdomain.com/llms.txt — the same location logic as robots.txt. An optional companion, llms-full.txt, can hold the expanded long version of your content.
Which AI systems actually read llms.txt?
Honest answer: no major vendor has formally committed to it, and adoption by crawlers is uneven. What is verifiable: a growing number of AI-adjacent tools and crawlers fetch it, and a clean llms.txt also serves as a well-structured summary any retrieval system can use. We surface whether your site has one because it's a measurable entity-clarity signal.
What's the difference between llms.txt and robots.txt?
Opposite purposes: robots.txt tells crawlers what NOT to access; llms.txt tells AI models what your site IS and which pages matter most. One restricts, the other explains. They coexist — you should have both.
How do I check if my site has llms.txt?
Open yourdomain.com/llms.txt in a browser — if you get a 404, you don't have one. Or run the free scan on this page with your website filled in: the Site Readiness half of the scorecard explicitly checks for llms.txt and schema.org markup.
Related tools & guides
llms.txt is one move of six
Entity clarity is a single item on the GEO checklist. See the whole playbook — and measure where you stand today.
Read the GEO guide