Before the Web became the place where a refrigerator can demand an account and a privacy policy, its first page had a simpler job: explain what the Web was and point people toward the software.
Visit the historic World Wide Web project page at CERN
CERN identifies info.cern.ch as the address of the world’s first website and web server. The first page address was /hypertext/WWW/TheProject.html, devoted to Tim Berners-Lee’s WorldWideWeb project.
The exact earliest page changed as the project developed, so what survives at the historic address should not be treated like a frozen byte-for-byte snapshot from one magical afternoon in 1990. What matters is that CERN has preserved the project and the address where the Web first explained itself.
A homepage before homepages had rules
The page is almost aggressively small.
It defines WorldWideWeb as a wide-area hypermedia information-retrieval initiative and then starts linking outward: project summaries, mailing lists, policy, software, technical documentation, people involved, project history, code and information about what was already available online.
There is even a section called “How can I help?”
Another link tells visitors how to get the code by anonymous FTP.
In 2026, that reads like archaeology. At the time, it was onboarding documentation.
By Christmas 1990, Berners-Lee had the first browser/editor and server running at CERN on a NeXT computer. CERN’s own history notes that the machine carried a handwritten warning telling people not to power it down because it was a server. The Web was global in ambition and still physically vulnerable to somebody reaching for the wrong switch.
The useful lesson for webmasters
The first website is not impressive because of its visual design. There essentially isn’t any.
It is useful because the information architecture is obvious. The page tells you what the project is, what exists, where to get software, how to learn more and who is involved. The links are the interface.
That is worth remembering after three decades of carousels, overlays, frameworks, cookie banners and buttons that animate because somebody had a quarterly objective.
CacheRat’s Ancient Web list contains 1,967 sites from later generations of that same medium: personal pages, hobby sites, technical archives and other things built before the Web settled into its current shape.
Explore the 1,967 Ancient Web Domains research list
The first page is still short enough to read in a minute. The consequences took a little longer.