Leafy
Look up any word on your screen without leaving the page
What it does
You hit a word you don't know. Three tabs later, the paragraph is gone. Hold ⌥A, box the word, and Leafy answers for that sentence instead of the dictionary's first guess, over PDFs, ebooks, images, anything on screen. Every word saves itself, then comes back blanked out in the sentence you met it in. 10 languages.
Leafy is a free macOS dictionary and vocabulary app. Press ⌥A to look up any word on screen: OCR reads it straight out of PDFs, scanned pages, ebooks, subtitles and images, and every lookup is saved with the sentence it came from. No account, no ads.
She had read the word a hundred times before, but only now, by the river at dawn, did it truly land: the water was effervescent , and for a moment the whole current seemed to lift and breathe, each ripple catching the first pale light and breaking it into a thousand small bubbles of gold that rose, trembled, and were gone before she could name them. She read the sentence again, slower this time, mouthing the word to feel its shape, and something about the morning, the cold air, the moving water, the hush over everything, made it stay with her for good. Saved, with the sentence. That's 1,204 words in your library. Every word you look up is saved with the sentence you found it in. Scheduling…from leafyapp.uk
Does the same job
all alternatives →
More ai this month
the category →
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
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 9d 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