minimind is the heat. Score 82.

Ask your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as sensors, four actions for automations, and a conversation agent for Assist.

HK is a unified neural model format and framework built in native Zig, designed to replace SafeTensors, GGUF, and PyTorch checkpoints. Features zero-copy mmap loading, dual-mode quantization, 2:4 hardware sparsity, live model expansion, and 137+ architecture support with bindings for Python, Rust, Go, C#, Java, and TypeScript.

A 777M-parameter Mixture-of-Experts language model trained from scratch for $55. Multi-head Latent Attention, DeepSeekMoE, own tokenizer.

Logic-based multi-LLM voice router for Home Assistant, combining native intents, local Qwen, GPU-aware desktop Ollama, and cloud AI with intelligent fallback.