Atlas
A companion to your creative works
What it does
Atlas is a native iOS and Mac workspace for writing, researching, and organizing your creative projects in one place. A bespoke Markdown editor sits at its core, paired with canvases, research storage, a web clipper, and flexible exporting tools. Atlas keeps you focused, gives your work a safe home, and brings just enough structure to support _your_ creative process, without getting in its way.
Found an article that sparks an idea? Clip it straight from Safari using the Web Clipper , where it becomes a searchable, taggable reference sitting right next to your writing. Pull in PDFs, images, and audio using the Save tool—so when inspiration strikes, you never have to remember which app you saved it in.Oh, and it’s all synced across your devices through iCloud just like your documents. Map your story’s world on an infinite canvas —pin characters, locations, and plot threads in space, then draw connections between them to see how everything relates. Link documents together with wiki-style references that update automatically when you rename things. Organize chapters,…from contagious.dev
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
The New Calendly▲211Handle all of the work before, during, and after meetings
Work · 17d ago · calendly.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 · 16d ago · simedw.com