{
 "url": "https://agenticweb.wiki/compare/html-dom-vs-markdown-for-agents/",
 "title": "HTML DOM & RSS vs Accept: text/markdown & OKF",
 "description": "HTML DOM & RSS vs Accept: text/markdown & OKF: Raw HTML pages typically spend 75–95% of their byte payload on layout boilerplate, navigation bars…",
 "markdown_url": "https://agenticweb.wiki/compare/html-dom-vs-markdown-for-agents/index.md",
 "markdown": "# HTML DOM & RSS vs Accept: text/markdown & OKF\n\nRendered HTML5 DOM, CSS/JS bundles & RSS/Atom feeds is the classic web primitive built for human browsers and pre-integrated services (Render visual layout, typography, and interactive widgets for a human in a browser viewport), whereas Markdown for Agents and its step 4 (Read) peers provide the machine-native agentic surface (Accept: text/markdown) so autonomous agents can answer: \"Can an agent ask a site for a Markdown version of an HTML page, instead of parsing the HTML itself?\" Across the agenticweb.wiki conformance panel, Markdown for Agents is shipping (136 of 136 probed origins (last checked 2026-10-23)).\n\nHow HTML DOM & RSS compares to Accept: text/markdown & OKF at step 4 (Read): why the classic primitive breaks for software agents, and how sites deploy both together.\n\n[4 Read](/category/read/) [Markdown for Agents](/protocols/cloudflare-markdown-for-agents/) · [Open Knowledge Format](/protocols/okf/) · [AGENTS.md](/protocols/agents-md/) · [Agent Readability Spec](/protocols/vercel-agent-readability/) · [Apache Ossie (formerly Open Semantic Interchange)](/protocols/osi/) · [The 'knowledge-linkset' Well-Known URI for Publishing Knowledge Artefacts](/protocols/knowledge-linkset/)\n\n| Dimension | Rendered HTML5 DOM, CSS/JS bundles & RSS/Atom feeds Classic web | [Markdown for Agents](/protocols/cloudflare-markdown-for-agents/) Agentic web |\n| --- | --- | --- |\n| Primary consumer | Human driving a web browser or pre-integrated developer code | Autonomous software agent, coding harness, or AI search/RAG crawler |\n| Lifecycle step | Classic web baseline for step 4 (Read) | 4 Read: Give me the content |\n| Core question answered | Render visual layout, typography, and interactive widgets for a human in a browser viewport. | Can an agent ask a site for a Markdown version of an HTML page, instead of parsing the HTML itself? |\n| Wire format & entrypoint | Accept: text/html (with navigation chrome, scripts, and inline SVG) | HTTP header at Accept: text/markdown |\n| Failure mode for agents | Raw HTML pages typically spend 75–95% of their byte payload on layout boilerplate, navigation bars, scripts, and hydration state—wasting context tokens and burying tables or specifications deep in the byte stream. | Solved natively: Markdown for Agents is a Cloudflare network feature: when an agent requests a page with Accept: text/markdown, an enabled zone fetches the HTML from the origin, converts it to Markdown at the edge and returns it as text/markdown with Vary: Accept, so caches keep the HTML and Markdown variants apart. |\n| Governance & status | Established IETF / W3C / industry baseline | Cloudflare; a feature of its network documented in Cloudflare's developer docs, not submitted to a standards body; it rides on ordinary HTTP content negotiation — Vendor feature, available to Pro, Business and Enterprise plans and SSL for SaaS customers at no cost; not a standards-track document |\n| Live adoption (/check/ census) | Universal across the classic web | shipping — 136 of 136 probed origins (last checked 2026-10-23) |\n| Primary specification | https://html.spec.whatwg.org/ | [https://developers.cloudflare.com/fundamentals/reference/markdown-for-agents/](https://developers.cloudflare.com/fundamentals/reference/markdown-for-agents/) |\n\n## Why HTML DOM & RSS breaks when the caller is an agent\n\nRaw HTML pages typically spend 75–95% of their byte payload on layout boilerplate, navigation bars, scripts, and hydration state—wasting context tokens and burying tables or specifications deep in the byte stream.\n\n## When to use which (and how they work together)\n\n- Keep Rendered HTML5 DOM, CSS/JS bundles & RSS/Atom feeds: A human visitor opens your URL in Chrome, Safari, or Firefox.\n\n- Add Markdown for Agents: An AI search crawler (Exa, Parallel.ai, OAI-SearchBot, ClaudeBot) or coding agent requests the same URL with Accept: text/markdown (or fetches <page>/index.md or /okf/index.md) to ingest clean, token-dense Markdown with Vary: Accept and x-markdown-tokens.\n\n## All agentic web standards replacing or extending HTML DOM & RSS\n\n- [Markdown for Agents](/protocols/cloudflare-markdown-for-agents/) — shipping · 136/136 probed origins: Can an agent ask a site for a Markdown version of an HTML page, instead of parsing the HTML itself?\n\n- [Open Knowledge Format](/protocols/okf/) (OKF) — shipping · 1/572 probed origins: How can an organization package durable, structured knowledge (schemas, metrics, playbooks, runbooks) so both humans and agents can read, produce, and trust it without a bespoke SDK?\n\n- [AGENTS.md](/protocols/agents-md/) — multi-implementation · 32/574 probed origins: What build, test, and convention instructions should a coding agent follow in this repository?\n\n- [Agent Readability Spec](/protocols/vercel-agent-readability/) (ARS) — shipping: How readable is this site's content for AI agents, and what specifically should be fixed?\n\n- [Apache Ossie (formerly Open Semantic Interchange)](/protocols/osi/) (OSI) — prototype: How can an AI agent or BI tool read a metric or data-model definition and get the same meaning another tool intended?\n\n- [The 'knowledge-linkset' Well-Known URI for Publishing Knowledge Artefacts](/protocols/knowledge-linkset/) — none found: How can a web origin publish, at one well-known location, a checkable list of the knowledge artefacts it offers (graph serializations, JSON-LD context, text file, chunk export, change ledger) so that agents can find them and verify digests?\n\nCheck whether any domain publishes these standards live at [/check/](/check/) or over MCP with probe and validate_manifest. [Connect](/connect/).\n\n[JSON](/compare/html-dom-vs-markdown-for-agents/index.json) · [Markdown](/compare/html-dom-vs-markdown-for-agents/index.md) · [cloudflare-markdown-for-agents.json](/data/protocols/cloudflare-markdown-for-agents.json)\n"
}