Fast, quiet
local notes
Drawn natively with Rust + GPUI, smooth even with million-character documents. Your notes stay on your computer, compatible with Feishu (Lark) docs.
Related
TensorFold | Run LLMs, Fast.
Run open models on the GPUs you own, with native Metal and CUDA inference.
Maple AI: Private AI Chat and Work
Lobe UI components for MyGo desktop apps, drawn on the GPU in pure Go.
https://x.com/oQuery/status/2119519954357944447/photo/1
JITEngine
LLM serving, synthesized for your Mac. Up to 2.7× as fast as the best other server we measured on the same Mac. We used…
fayazara's GitHub
Another dev with a lot of projects like OpenClaw creator Peter Steinberger. Found via announcement of lotion - local…
Lucebox: Your local inference AI workstation
DeepSeek V4.1 Flash, running 24/7. 54 tok/s decode. $8,199. https://shop.lucebox.com…
