llms.txt生成器:让AI引用你内容的站点地图
llms.txt告诉AI爬虫你的网站有什么。
llms.txt Generator 2026: The AI Site Map That Gets Your Content Cited
llms.txt is a proposed standard (introduced by Jeremy Howard in 2025) - a single markdown file at your site root that tells AI crawlers what your site has and which pages matter. It is the AI-era sibling of robots.txt and sitemap.xml. Perplexity, ChatGPT Search, and other AI tools increasingly consult it.
Why It Matters
- AI crawlers can read it in one request instead of crawling hundreds of pages
- You control which pages are "featured" (the ones you want cited)
- It gives context ("this is a coupon site", "these are our top guides") that raw crawling misses
- Early evidence suggests cited pages correlate with what's listed in llms.txt
The Format
# Example Corp
A short description of the site and what it covers.
## Featured Posts
- [How to Reduce AI Token Costs](https://example.com/token-costs): A practical guide with benchmarks
- [Local LLM Setup Guide](https://example.com/local-llm): Hardware and model picks
## Pages
- [Home](https://example.com)
- [About](https://example.com/about)
## Site Info
- Languages: English, Chinese
- Topics: AI, Tutorials
How to Generate It
Option 1 - Hand-written (best for small sites). One file, 30 minutes. Just list your best 10-20 pages with one-line descriptions.
Option 2 - llms.txt generator tools. Several open-source generators exist on GitHub (search "llms.txt generator"): they crawl your sitemap.xml and emit the markdown.
Option 3 - Python script. Read sitemap.xml, extract titles/descriptions from pages, write the markdown:
import xml.etree.ElementTree as ET
tree = ET.parse("sitemap.xml")
urls = [u.findtext("{http://www.sitemaps.org/schemas/sitemap/0.9}loc") for u in tree.getroot()]
# write urls into the llms.txt format
Placement Rules
- File must be at https://yoursite.com/llms.txt (root, not /llms.txt.txt)
- Keep it short - 50 entries max, curated
- Update it when you publish important new content
- Link to it from your footer or robots.txt
FAQ
Is llms.txt a ranking factor? Not officially, but it improves retrieval, which improves citations. Think of it as making your content easier to find and summarize.
llms.txt vs sitemap.xml? Sitemap is for search engines; llms.txt is curated for AI tools. You want both.
Does it hurt SEO? No - it is an addition. Google ignores it; AI tools use it.
