Custom Swift and Metal runtime enabling 26B instruction-tuned model inference in around 2 GB RAM by streaming weights from SSD, optimized for Apple Silicon Macs.
Platforms
- Mac
United Kingdom

Custom Swift and Metal runtime enabling 26B instruction-tuned model inference in around 2 GB RAM by streaming weights from SSD, optimized for Apple Silicon Macs.

AURA is an open-source Android app for AI face reading (physiognomy) and palm reading. The key idea is privacy: your photos never leave your device. All analysis runs locally using Google Gemma (on-device LLM) and MediaPipe for detection, so nothing is uploaded to a server.



Greenative Studio lets you run local LLMs with your files, tools, and coding agents - without sending sensitive data or source code to cloud AI services.



WebBrain is a free, open-source browser extension that brings AI agent capabilities to your browser. Read pages, extract data, and automate web tasks — powered by your choice of LLM. The self-hostable alternative to proprietary browser AI plugins.



