A TikTok-style vertical feed where a voice agent narrates the card you're on and shuts up the instant you swipe. The engine is open source. The lessons that make it feel right — the ones that don't leak in a screenshot — are the kit.
MIT engine · founding price through Aug 1, 2026 · free updates
A swipe feed is the inverse of a normal voice assistant. There, the user speaks and waits. Here, the agent must narrate the on-screen card the instant it lands — and go silent the moment you swipe again.
Narrate in a 3–4 second hook, not a paragraph. A card that takes ten seconds to describe is a card the user already swiped past.
On swipe, cut the audio instantly and re-narrate the new card. A soft fade reads as the agent ignoring you.
A fast scroll fires a flood of updates. Un-debounced, they starve the user's turn — and the agent stops being able to hear you.
Every part of the product, laid out. Open the free ones and read the real code. The locked ones show you exactly what you'd get — because the title is the point.
Battle-tested = shipped and survived production. Would-do-differently = an informed correction. Both are in the kit; they're labeled so you always know which is which.
"Three weeks in at roughly 20% focus — and only that fast because I reused prompts from an earlier ElevenLabs→Bubble build. Without that head start: one to two days planning, several days testing, several more optimizing."
— the builder. The kit is that head start.
The narration-sync problem, the architecture, the method — the parts that aren't code. One email, one link, no spam.