Cadencz
You focus on your product, we focus on your marketing
What it does
Cadencz is an AI social media manager for founders and lean teams. Seven AI agents learn your product and voice, plan your week, write platform-native posts, check every draft for quality, and send approved content to your calendar. Publish across nine live platforms: X, LinkedIn, Threads, Bluesky, Mastodon, Telegram, Discord, Slack, and dev.to. Every AI-generated post waits for your approval by default, so nothing goes live without your say.
Eight AI social media agents read your site, plan, write, critique, schedule, and publish approved content across 9 live channels.
Cadencz is an AI social media workspace for founders . It remembers your product and voice, drafts for your chosen channels, and keeps review and publishing together. You approve posts by default. Free, no card. Start with 2 drafts per plan and 10 AI generations a month. Cadencz keeps the research, writing, approval, publishing, and feedback together in one content workflow , so your agents never lose the reason behind the work. Paste one URL. Cadencz reads your product, positioning, audience, proof points, competitors, and writing style before it drafts a word. Every agent has one job and reads the same product context. Ideas become platform-native drafts, weak copy is rejected, and the…from cadencz.com
Does the same job
all alternatives →More growth this month
the category →
AstraPixels▲267A pixel-art solar system at its real current positions.
Growth · 29d ago · astrapixels.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