LinkJeremy HowardResource
Raw HTML layouts waste model context with boilerplate, ads, and JavaScript. As AI agents increasingly browse the live web to fetch technical documentation or business facts, llms.txt establishes a lightweight, vendor-neutral standard to deliver concise context directly.
Choosing Markdown over formats like XML or JSON allows direct consumption by LLMs while maintaining strict structural parsing rules. The path-based approach solves deployment constraints on shared hosts (such as GitHub Pages) where RFC 8615 well-known endpoints are inaccessible. Broad ecosystem adoption across platforms like GitBook, Mintlify, and WordPress demonstrates strong momentum for agent-first web standards.
Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
Link:agentwikis.com
Agent Wikis transforms fast-moving information sources such as repositories, changelogs, transcripts, and community Q&A into structured Markdown knowledge bases. Designed for both humans and AI agents, the content is accessible via an llms.txt entry point.
Link:specification.website
The Website Specification (specification.website) is a platform-agnostic, open-source guide licensed under MIT, detailing the technical features a good website should implement. It spans HTML foundations, SEO, accessibility, security, and agent readiness, offering direct Markdown access, an MCP server, and an Agent Skill.
Link:Anthropic
Agent Skills is an open format designed to equip AI agents with specialised domain knowledge and repeatable workflows. Centred around a directory containing a SKILL.md file, it relies on progressive disclosure to keep context overhead minimal.
Article:Google Chrome Developers Team
Google has documented an experimental Lighthouse category designed to evaluate how well websites interact with autonomous AI agents, using pass/fail checks rather than a 0-100 score.
Repository:Podcast72/showroom-la-finestra-webmcp
The showroom-la-finestra-webmcp repository demonstrates how existing websites can expose structured business knowledge and safe actions directly to AI agents without running a separate MCP server. By using an in-browser layer via `document.modelContext`, the website explains itself rather than relying on DOM scraping.
1starsJavaScript
Link:Joost de Valk
Joost de Valk explores the evolution of websites in the age of AI agents. Rather than disappearing, websites are shifting from human-only HTML pages into canonical systems of record. They must serve as interface bundles—including protocols like MCP—that allow automated agents to read data and take actions, while verifiable authenticity remains the only lasting competitive moat.
Parts of this content were created with the assistance of AI.
