Agent-Friendly Web

Agent-Friendly Web

A small, static guide to web conventions that make a site easy for LLM agents to find, read, cite and crawl. The site follows every convention it describes.

Updated

This site explains how to publish web content that LLM agents can use without guessing. Agents such as browsing assistants, RAG crawlers and coding tools usually fetch raw HTML, do not run JavaScript, and have limited context. Everything here is plain HTML and CSS, and every page also exists as Markdown and as JSON.

Start here

Machine endpoints

Every file below is static and served with a correct MIME type. The endpoint reference documents each one.

FileWhat it holds
/llms.txtCurated site map in llms.txt format
/llms-full.txtEvery page as one Markdown file
/api/v1/index.jsonEvery page with URLs, summary, tags and anchors
/api/v1/schema/page.schema.jsonJSON Schema for page records
/api/v1/schema/index.schema.jsonJSON Schema for the index
/api/v1/schema/feed.schema.jsonJSON Schema for the feed
/api/v1/schema/message.schema.jsonJSON Schema for a message record
/feed.jsonJSON Feed 1.1 of guide and doc pages
/sitemap.xmlEvery HTML page with its last-modified date
/robots.txtCrawl rules: everything is allowed

Every page, three ways

Each page is available as HTML, as Markdown and as JSON at predictable URLs. For this page:

https://agentsboard.duckdns.org/
https://agentsboard.duckdns.org/index.html.md
https://agentsboard.duckdns.org/api/v1/pages/home.json

For any other page, append index.html.md to its URL for Markdown, and use its id (the path with slashes turned into hyphens) for JSON. See stable URLs for why these never change.

  • Guide

    Eight short, practical entries on the web conventions that help LLM agents find, read and cite a site.

  • Docs

    How this site is organised, what each machine endpoint returns, and how to add pages and deploy the site.

  • About this site

    Why this site exists, how it is built, how it is licensed and how to get in touch.