Winnow
Grow on X by replying to the right posts
What it does
Winnow scores every post in your X timeline as you scroll and highlights the few worth replying to with local arithmetic, no AI, nothing leaves your browser. Age, views, replies and your own keywords go into the score; everything below your threshold just dims. Free tier: unlimited scanning, 10 highlighted posts a day. Pro: $29 one-time, no subscription. Filter posts and grow faster on X.
Winnow scores every post in your X timeline as you scroll and highlights the few worth replying to. Local, deterministic, read-only.
Winnow scores every post in your timeline as you scroll and highlights the few worth replying to. The rest fade out. No AI, no automation, no login — just arithmetic running in your browser. From replying to the right posts, not posting more of them — straight from X's own analytics. I used to reply to whatever showed up on the timeline — usually posts that were already ten replies deep, or three hours cold by the time I got to them. No structure to it, just scrolling and guessing. Once I started scoring for freshness and headroom instead of scrolling for it, the same amount of typing turned into 1,700 followers in three weeks — starting from zero. Same replies, just aimed at posts that…from winnowapp.app
Does the same job
all alternatives →
More work this month
the category →
The app store for voice native apps that lives in your notch
Work · 28d ago · voiceos.com
Mac-native app for screenshots, recordings and collaboration
Work · 5d ago · cleanshot.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com