Every Skill, MCP server, CLI and plugin in the directory. Filter by type, profession or tag, or search by keyword.
Pick one or more: resources that suit any of them are listed.
Pick one or more: only resources carrying all of them are listed.
1 item
Local LLM inference engine in plain C/C++ with a command-line chat and an OpenAI-compatible HTTP server; pulls and runs GGUF models straight from Hugging Face. Supports Apple Silicon, CUDA, Vulkan and other hardware, plus low-bit quantization.
