SKaiNET Developers

Open-source deep learning framework simplifies creation of modern AI applications, adhering to GitFlow for branching and Semantic Versioning for release management.

#ai

High-performance LLM application layer offering runtimes and CLI tools for Llama, Gemma, Qwen and BERT models; safetensors model loading and hardware-accelerated inference.

#sdk, #performance-optimization, #llm, #fileformat, #file, #command-line-interface, #ai, #agents, #agentic-ai

Interactive Jupyter notebook integration enabling deep-learning experimentation with type-safe tensors, inline image/Graphviz rendering, autograd graph visualization, SIMD-accelerated and quantized kernels.

#wasm, #sdk, #rendering, #performance-optimization, #math, #image, #ai

Automatic differentiation library enabling compile-time optimization of mathematical expressions, featuring multi-module architecture, KSP-based code generation, and computational graph visualization through Graphviz.

#math, #ksp, #code-generation, #ai

Audio preprocessing and streaming utilities: resampling to 16 kHz mono, ByteArray WAV codec, whisper-verified log-mel spectrograms, chunk-independent windowing, VAD producing line-oriented events.

#kotlin-flow, #fileformat, #device, #coroutines, #audio