Reproducible local LLM setup and benchmark evidence for AMD Strix Halo / Ryzen AI MAX+ 395: 63-98.5 t/s direct Qwen MoE, 101.1 t/s MTP.

A production-grade Python SDK for the Lemonade LLM backend. Featuring auto-discovery, port scanning, and a low-overhead client architecture. Powering the Sorana AI workspace.

Demo to showcase Strix Halo memory QoS under concurrent AI + CPU workloads (Ollama + CMake + Python).

Hyperspace Vision API, interfaced with ion CI build system (CMake)

Sample MCP Server for weather queries - Reference implementation for ASUS and OEM partners

Menu-first CLI for inspecting and benchmarking local AI accelerators across CPU, GPU, and NPU