Partially Verified65% confidenceFactExact time
llms.txt has a different positioning from robots.txt (which controls crawler access permissions) and sitemap.xml (which lists URLs); its goal is to let models quickly understand a site's structure and core content.
3
Sources
65%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDo not directly copy and paste sitemap.xml as llms.txt; the two have different design goals: the former is designed for crawlers but is not suitable for models to quickly understand the site.79% similarUnverifiedLinks in llms.txt should use absolute URLs, because readers may parse the file out of context and have no reliable base for resolving relative paths.77% similarPartially Verifiedllms.txt is an emerging convention in which a website explains its own structure, core content and licensing terms to models in Markdown format.76% similarUnverifiedWebMCP is regarded as the third category of machine-oriented website meta-information standards, following robots.txt and sitemap.xml.75% similarUnverifiedThe llms.txt convention places the file at the site root path (such as example.com/llms.txt), uses plain Markdown format, and lets an Agent obtain the navigation structure of the entire site's documentation with a single lightweight request.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1021202API
curl https://kongchang.com/api/v1/knowledge/claims/1021202MCP
get_claim(id=1021202)