We need RSS for sharing abundant vibe-coded apps
As LLM-assisted development accelerates, the friction of app distribution is becoming a bottleneck. Simon Willison and Matt Webb surface a real infrastructure gap: when Claude and similar tools make building micro-apps trivial, developers need a standardized way to share and discover these tools without friction. Webb's observation that vibe-coded apps are more like blog posts than traditional software launches points to a shift in how AI tooling will be consumed and distributed. The missing piece is a feed protocol that treats installable tools as first-class content, similar to how RSS democratized blog discovery. This reflects a deeper landscape change where AI-native development workflows are outpacing the distribution mechanisms built for traditional software.
Modelwire context
Analyst takeThe framing here isn't really about RSS as a technology, it's about who owns the discovery layer when app creation becomes nearly free. That ownership question has significant commercial stakes that neither Willison nor Webb fully surfaces.
This is largely disconnected from recent activity in our archive, so it's worth placing it in a broader context. The argument belongs to an emerging conversation about AI-native distribution infrastructure, sitting adjacent to debates about agent marketplaces and tool registries that platform players like Anthropic, OpenAI, and browser vendors are already quietly positioning around. The analogy to RSS is instructive precisely because RSS won the protocol battle and lost the distribution war to aggregators. A standardized feed format for micro-apps could follow the same path: open spec, closed discovery surface.
Watch whether Claude.ai, Replit, or a browser vendor ships a native feed-subscription mechanism for user-built tools within the next six months. If one of those closed platforms moves first, the open-protocol window closes fast.
This analysis is generated by Modelwire’s editorial layer from our archive and the summary above. It is not a substitute for the original reporting. How we write it.
MentionsSimon Willison · Matt Webb · Claude · RSS · Atom
Modelwire Editorial
This synthesis and analysis was prepared by the Modelwire editorial team. We use advanced language models to read, ground, and connect the day’s most significant AI developments, providing original strategic context that helps practitioners and leaders stay ahead of the frontier.
Modelwire summarizes, we don’t republish. The full content lives on simonwillison.net. If you’re a publisher and want a different summarization policy for your work, see our takedown page.