mritzco/strixhalo-recipes

Control panel for VLLM, Sglang, llama.cpp, exllamav3

Advanced CLI tool that scans your hardware and tells you exactly which LLM or sLLM models you can run locally, with full Ollama integration.

HF CLI extension to run local coding agent powered by llmfit and llama.cpp

Honest local LLM deployment planning and benchmarking for high unified-memory Macs and future Linux/NVIDIA rigs.

Pi extension for llama.cpp integration

This repository builds llama.cpp for Strix Halo devices.

Local AI registry: one validated recipe per machine, with the evidence attached

Windows Hardware Diagnostic & Local AI Model Advisor. Fast in-process hardware detection & intelligent local LLM recommender for Ollama.

pi.dev + llama.cpp ❤️