@shokhkarim1212 · X

@SimonKroisi · X

@vanta_ui · X

UI Library built from real products

Loerei · HN

I found that describing where a broken UI is and taking screenshots for AI agents really sucks. I’m too lazy to explain an indescribable visual bug or capture a millisecond-long flash. I also don’t want to remember which file defines an element, whether it's right in the .tsx or a problem with the Parent Styles in .css. And even if you can point out the exact file, your agent still has to dig through thousands of lines of code to know what on earth you're yapping about. In a 7700-file monorepo like Cal.com, simply giving the right file in the prompt for your agent saves about 68.9% of execution time and 94.2% of the tokens your agent needs to digest. HoverSource gives all the needed information and further pushes it to -88.5% time and -94.5% tokens, basically skipping the entire digging session and jumping straight to reasoning and executing. The save is linear to how big your codebase is. I want to save tokens, but don’t want to spend my time and energy digging manually, and a junio

@ArthurMrcnr · X

@Ksparth12 · X

@casancamdev · X

@yeasindesign · X

Beautiful prompt library

@radomir_3 · X

Let’s connect. I’m building App screenshot studio

@MSiatrak · X

Checked my Umami stats this morning - straight from Claude Code via my Umami MCP 📊 ~30% of visitors are on mobile… and every single one hit the "desktop only" gate. Shown 11 times, 0 continued past it. A third of traffic couldn't even try it.

@jf_watcher · X

@buildwithshyam · X