llms-txt (Answer.AI reference tooling): vendor profile

In short

The llms-txt Python module reads an llms.txt someone else wrote: it parses the sections, can skip the Optional one, and offers XML output because some models prefer it. Proposal v2 adds rel=alternate and rel=describedby links and accepts page.html.md or page.md as copy URLs. The code is Apache-2.0 licensed.

At a glance

standards.txt llms-txt-python

llms-txt               = supports
markdown-negotiation   = no statement
markdown-twin          = supports
initial-html           = no statement
real-404               = no statement
vary-accept            = no statement

2 supports, 0 partial or announced, 4 no statement.

llms-txt Markdown or llms.txt tool

The Python module published with the llms.txt proposal: it parses an llms.txt file into sections and expands the linked files into an XML context, alongside the proposal text that defines the file and the .md page copies.

Type: Markdown or llms.txt tool
Operator, as the facts below state it: Answer.AI
Home page: llmstxt.org, answered HTTP 200 on 2026-11-05
Last read: 5 November 2026

What it does for this layer

The llmstxt.org core module implements parse_llms_file, which pulls the sections of an llms.txt into a simple data structure. [primary source] source, read 5 November 2026.
The llms-txt module builds a Project with one Section per H2 part of the file and can skip the section named Optional. [primary source] source, read 5 November 2026.
The llms-txt module offers an XML output because, its docs say, some LLMs such as Claude prefer XML. [primary source] source, read 5 November 2026.
The v2 changes page says the llms_txt2ctx context-expansion tool is no longer part of the proposal; agents are expected to read llms.txt and follow its links. [primary source] source, read 5 November 2026.
Proposal v2 adds rel="alternate" type="text/markdown" for a page's markdown copy and rel="describedby" for the llms.txt that covers it, as HTML link elements or an HTTP Link header. [primary source] source, read 5 November 2026.
Proposal v2 accepts both page.html.md and page.md as markdown copy URLs and says the most specific llms.txt in a subpath applies. [primary source] source, read 5 November 2026.
The llmstxt.org page lists August 10, 2026 as its modified date. [primary source, 2026-08-10] source, read 5 November 2026.
llmstxt.org says all nbdev projects now create .md versions of every page by default. [primary source] source, read 5 November 2026.
The AnswerDotAI/llms-txt repository on GitHub is published under the Apache-2.0 licence. [primary source] source, read 5 November 2026.

Products and plans

Plans and prices as the vendor's own pages showed them on the date read.
Product	What it is	Price	As of	Source
llms-txt Python module	Parser and context builder for llms.txt files, documented on llmstxt.org.	Free, open source Apache-2.0	2026-11-05	source

Standards

The six standards this site tracks; no statement means the pages read said nothing.
Standard	Status	What the vendor's pages say	Source
llms-txt	supports	Reference parser and the proposal text itself.	source
markdown-negotiation	no statement	The proposal pages read define link relations, not Accept-header negotiation.	none
markdown-twin	supports	v2 defines page.html.md and page.md copies.	source
initial-html	no statement	Out of scope for the module.	none
real-404	no statement	Out of scope for the module.	none
vary-accept	no statement	Out of scope for the module.	none

Checks on its own site

Readings of llmstxt.org, the vendor's own website, which describe that site and not the product.
Reading	Result	Date
Home page request	HTTP 200; H1 in the initial HTML: yes; 1,801 words; 0 JSON-LD blocks	2026-11-05
Request with Accept: text/markdown	HTTP 200, text/html, Vary: Accept-Encoding	2026-11-05
/llms.txt at the host root	HTTP 200, text/plain, 637 B, starts with an H1	2026-11-05
A made-up path	HTTP 404	2026-11-05
Ora score, cached	44, grade D	2026-10-11
Cloudflare keyless scan	7, L0 Not Ready	2026-11-05
Shared crawl row	outside the ranked slice; home page HTTP 200; H1 in the HTML: yes; 1,896 words; JSON-LD types: none; answers markdown: no; made-up path HTTP 404; llms.txt valid: yes	2026-11-04

What it does not do

The llms-txt module does not generate an llms.txt from a website; it reads and expands a file someone has already written.

Related pages on this site

Sources

The /llms.txt file, v2: llms-txt https://llmstxt.org/, read 5 November 2026
Python source: llms-txt https://llmstxt.org/core.html, read 5 November 2026
Changes: llms-txt https://llmstxt.org/changes.html, read 5 November 2026
GitHub - AnswerDotAI/llms-txt: The /llms.txt file, helping language models use your website · GitHub https://github.com/AnswerDotAI/llms-txt, read 5 November 2026

Last reviewed 5 November 2026