About

The web remembers
everything

html.surf is a knowledge platform built on one idea: HTML is the right format for knowledge. Not Markdown converted to HTML. Not JSON fetched into a React component. Real, linkable, traversable HTML — the way the web was designed to work.

Why HTML?

Every knowledge tool eventually asks how to expose its data to AI. The answer is almost always: add an API, write a parser, build a connector. HTML doesn't need any of that. It's already structured. Links are already relationships. Headings are already hierarchy. The semantic web people were right — they just built the wrong tools.

html.surf stores your pages as real HTML and serves them as real HTML. A human can read them in a browser. An AI can traverse them via MCP. A curl command can fetch them. Nothing in between.

The graph

Pages link to each other. Every link is tracked. Every backlink is surfaced. You build a knowledge graph just by writing — no ontology required, no schema to maintain. The structure emerges from the content.

The navigator agent traverses this graph to answer questions. It follows links, reads pages, and reasons across the graph the same way a human researcher would — starting from one page, following threads, building up context.

MCP-native

html.surf exposes your knowledge via the Model Context Protocol out of the box. One config line and any AI assistant — Claude, Cursor, any MCP client — can read and write your pages. Your knowledge graph becomes a tool your agents can actually use.

The MCP server has 24 tools: read, write, search, link traversal, sharing, permissions, themes, assets, and bookmarks. It's not a read-only export. It's a full interface.

Built for now

Most knowledge tools were built before AI agents existed. They store data in formats that require extraction, parsing, transformation before an agent can use them. html.surf was built with AI-native access as a first-class requirement — not a feature added later.

At the same time, it's still just a website. You can use it with no AI at all. Write pages, link them, share them. The hypermedia fundamentals are solid enough to stand on their own.

At a glance
24MCP tools
page graph depth
0lock-in (it's just HTML)
Principles
HTML is the formatNot a source that compiles to HTML. The content is the HTML.
Links are dataEvery link is tracked. The graph is a first-class citizen.
AI is a readerAgents access knowledge the same way humans do — by traversing the graph.
No lock-inExport as HTML, Markdown, or DOCX any time. Your content stays yours.
Get started →Read the docs