-
oboroge0/hayamimi
[427]
#Python
1 day
早耳 - Real-time multilingual speech-to-text on CPU only. Live subtitles, browser dashboard, speaker labels, translation. No GPU, no cloud.
-
AlexsJones/llmfit
[37663]
#Rust
7 days
Hundreds of models & providers. One command to find what runs on your hardware.
-
magnitudedev/magnitude
[6657]
#Rust
7 days
Open source inference engine for agents that optimizes itself for your exact hardware. Compiles and tunes its kernels on your device, so open models run up to 2x faster than llama.cpp. Works on Apple Silicon, NVIDIA, AMD, or just a CPU.