Run LLMs on AMD Vega8 / Vega10 APUs and GPUs (Ryzen 5700G / gfx90c and Vega 56/64): ROCm 7 gfx900 backport + Vulkan/RADV launchers, Docker images, benchmarks for llama.cpp and LM Studio

Monorepo of 4 healthcare AI agent skills: chart review, HEDIS NLP, HCC NLP, HIPAA compliance. Install: npx skills add Yar177/medical-chart-review-skill --skill '*'

Agentic auditor that flags unsubstantiated CMS-HCC risk-adjustment codes in clinical documentation, grounded against a deterministic Rust scoring engine as a verifiable oracle. Built on synthetic data.

Local speech-to-text toolkit for Arch Linux. Transcribes audio/video to clean Markdown via whisper.cpp (Vulkan/RADV). CLI-first: local files, YouTube, Telegram, dictation, LLM cleanup. Clean text by default, timestamps optional. GPU: AMD RX 580 via RADV