I put AI inference on devices, and terminals on Vision Pro.
- llama.rn
โ React Native binding for llama.cpp. LLMs running fully on-device, no server.
- llama.node โ llama.cpp for Node.js / WASM, same llama.rn API.
- whisper.rn
โ React Native binding for whisper.cpp. On-device speech recognition.
- whisper.node โ whisper.cpp for Node.js / WASM, same whisper.rn API.
- Collaborator on llama.cpp (31 PRs merged) and contributor to whisper.cpp (14) โ most of that work flows straight back into the bindings above.
- Multiplex โ an SSH / tmux / herdr terminal built for Apple Vision Pro, iPad and iPhone. Available on App Store, and Open-source.
Building BRICKS โ an application system for interactive content โ and CTOR, our agent harness & desktop IDE for it.
react-native-debugger (โ 10k, unmaintained) ยท react-native-external-display ยท redux-devtools-extension ยท electron-react-boilerplate
๐๏ธ Big 3 and old-school training ยท ๐ Japanese (JLPT N2+) ยท ๐ฆ @jhen_jie