Focu
Mindful productivity app for MacOS
What it does
Transform your relationship with work through AI-powered guidance, meaningful conversations and periodic check-ins. Focu uses a locally running AI that works privately and offline on your own Mac, data never gets sent to the cloud and stays yours.
Does the same job
all alternatives →- FOFocu, open-source mindful productivity app for macOS2025 · github.com · ▲5
I've been building Focu, a mindful productivity app for macOS, these past months. As someone diagnosed with ADHD and depression, it's been super helpful to journal daily and use an AI to reflect and get feedback. It's not a replacement for therapy, but it sure has been complementary. The app uses Ollama to provide the user with a locally running AI, the downside is that it does require a powerful device, but I've had super good results with Llama3.2:3b which is not too heavy to run at all. I'm using Dexie.js to store the data in IndexedDB although I'm considering moving to "file over app".…
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 · 26d ago · cactuscompute.com
