Stanza App
Offline grammar fixing with one click - Local, BYOK, Cloud
What it does
Stanza fixes grammar anywhere on your Mac using a single shortcut. Select text, press Cmd + Shift + G, and it replaces the corrected version instantly. No underlines. No popups. No copy-paste. Run it offline with Local AI (Auto Setup), use your own API key (BYOK), or use Stanza Cloud with zero setup. Built for people who want clean writing without breaking their flow.
Does the same job
all alternatives →
- FIFixkey is a keyboard-focused AI copilot for writing2024 · fixkey.ai · ▲36
Demo: https://www.youtube.com/watch?v=sRFOWNpb3U4 Imagine having the CMD+K functionality of Cursor.sh but instead of code you edit natural language. *Introducing Fixkey:* - Native Swift macOS app (no Electron) - Keyboard-centric - Select common prompts with keyboard shortcuts - Press one shortcut to select and fix the current paragraph - Create custom prompts just in time - Works in every application on macOS (Apple Notes, Obsidian, Notion, Gmail, Slack…) - Support for local running models (Beta) *Why not using Grammarly?:* I always feel that traditional grammar correction…
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 · 17d 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 · 27d ago · cactuscompute.com
