shadcn/ui
shadcn/ui is turning a component registry into infrastructure for AI app UIs.
A side-by-side editorial comparison of Air and Visily — release velocity, themes, recent moves, and the top alternatives to consider.
| Feature | Air | Visily |
|---|---|---|
| Sector | Design | Design |
| Velocity score | 8.8 | 0.0 |
| Sparks · 30d | 1 | 0 |
| Top themes | dam, creative-agents, canvas, localization | ai-design, wireframing, code-generation, figma-import |
| Last editorial update | 4d ago | 12d ago |
| Website | — | — |
Air's asset library grew an agent, and the agent is learning to keep what it does.
Canvas has become the centre of the product. In the last three weeks it gained an agent that edits existing video rather than only generating new clips, two additional video models, the ability to save any completed workflow as a reusable skill, @ mentions that pull in board assets alongside Brand Kit colours, fonts and logos, and now in-image text translation across 33 languages. The library side kept moving too, with manual person tagging where facial recognition falls short, current-version share links, frame-level timeline zoom, and a batch of video features covering burned-in captions, transcript editing and sub-clipping.
AI wireframing tool closing the loop from prompt to design to code
Visily's dated update posts show a steady march up the fidelity ladder. March added code generation for designs, a Plan Mode for ideation ahead of AI generation, and unsupported font replacement on Figma imports. February brought Figma import itself and blur effects; January added Design Instructions for consistent output and a Deep Design mode. Earlier releases covered shadows, a browser capture overlay, an AI Content Filler and interactive dropdowns.
Canvas has become the centre of the product. In the last three weeks it gained an agent that edits existing video rather than only generating new clips, two additional video models, the ability to save any completed workflow as a reusable skill, @ mentions that pull in board assets alongside Brand Kit colours, fonts and logos, and now in-image text translation across 33 languages. The library side kept moving too, with manual person tagging where facial recognition falls short, current-version share links, frame-level timeline zoom, and a batch of video features covering burned-in captions, transcript editing and sub-clipping.
Air is converting a digital asset manager into a place where assets are produced and adapted, not just stored and approved. The skills feature is the pivot point: it turns one-off agent instructions into named, repeatable operations, which is how a creative team's conventions become part of the tool. Brand Kit entering the @ mention namespace points the same way — the agent is being given the brand's own vocabulary as addressable material, so generated work starts from house colours and logos rather than a generic prompt.
Expect skills to gain sharing or workspace-level scope, since a saved workflow is far more valuable to a team than to the person who recorded it. The translation and captioning work together suggests localisation is being assembled as a workflow rather than left as isolated features.
Visily's dated update posts show a steady march up the fidelity ladder. March added code generation for designs, a Plan Mode for ideation ahead of AI generation, and unsupported font replacement on Figma imports. February brought Figma import itself and blur effects; January added Design Instructions for consistent output and a Deep Design mode. Earlier releases covered shadows, a browser capture overlay, an AI Content Filler and interactive dropdowns.
The arc runs from making generated designs look right to making them useful downstream. Design Instructions and Deep Design addressed consistency and polish; Figma import opened a migration path in; code generation opens an exit path out. Plan Mode is the interesting addition — separating intent from generation, rather than treating one prompt as the whole brief.
With import from Figma and export to code both in place, expect the round trip to tighten — keeping generated code and design in sync is the obvious unsolved half, though the entries do not describe work on it yet.
Other Design products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either Air or Visily.
shadcn/ui is turning a component registry into infrastructure for AI app UIs.
Two release trains, zero new features — Astra has been in pure maintenance mode since spring.
The editor now prints to a CVS counter, and that is the second business bolted on this summer.
Steady 1.3 maintenance, with the Lua API quietly becoming Aseprite's extension point.
Webflow is building for the answer engines, not just the search results page.
The 10.6 alphas are an Angular tooling rebuild wearing a version number.
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
They serve adjacent needs but don't currently overlap on shipped themes. Air is currently shipping more aggressively (velocity 8.8 vs 0.0), with 1 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. Air is currently shipping more aggressively (velocity 8.8 vs 0.0), with 1 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other Design products to evaluate alongside.
Top Air alternatives in Design are ranked by recent ship velocity. Browse the "Air alternatives" section above for the current picks, or visit /alternatives/air for the full list with editorial commentary on each.
Top Visily alternatives in Design are ranked by recent ship velocity. Browse the "Visily alternatives" section above for the current picks, or visit /alternatives/visily for the full list with editorial commentary on each.