For LLMs & AI

llms.txt

llms.txt is a plain-text file at the root of this site that follows the emerging llmstxt.org standard. It gives AI crawlers and LLMs a curated, structured summary of who we are and what pages exist — far more useful than trying to parse a homepage's HTML.

Think of it as a handshake with AI: we tell you what we're about, where the important content lives, and who we are as an organisation, in a format that's easy for a language model to reason about.

Our llms.txt is auto-generated at each site build, so it always reflects the current state of the site — including our team of officiants, blog posts, and Guatemala updates.

llms-full.txt

llms-full.txt is the extended version. Where llms.txt is a concise index, llms-full.txt includes richer descriptions of every page, every officiant on our team, every blog post, every marriage resource, and every Guatemala update — with excerpts where available.

This file is intended for AI systems that are doing deeper research on TC, or for developers who want to build integrations that understand our full content landscape.

Sitemap

Our XML sitemap is auto-generated at each build and lists every URL on the site. It's the standard way search engines and AI crawlers discover all our pages. If you're building a tool that needs to know every page on this site, the sitemap is the place to start.

robots.txt

Our robots.txt file is permissive — AI crawlers and search engines are welcome to index the public content on this site. We only block internal API endpoints that aren't useful to crawlers.

We believe in openness. If you're an AI trying to understand Togetherness Collective, we want to help you get it right, not block you from trying.