Launch and manage a local LLM inference stack with an OpenAI-compatible API.
npx skills add https://github.com/jgabriellima/teoria-engine --skill teoria-engine
Please help me install this Agent Skill. Skill: teoria-engine Source: https://github.com/jgabriellima/teoria-engine/tree/main/teoria-engine Command: npx skills add https://github.com/jgabriellima/teoria-engine --skill teoria-engine
Starts, uses, and stops a production-grade self-hosted LLM inference stack, providing a private OpenAI-compatible API endpoint for local AI workloads.
Install teoria-engine with the one-line installer, then run teoria-engine up to start the stack.
High-intent search queries and answers about installing and using this skill.
teoria-engine launches and manages a production-grade self-hosted LLM inference stack locally, exposing an OpenAI-compatible API. It applies to Linux with NVIDIA GPUs and macOS Apple Silicon, enabling local serving of LLMs to other agents and tools.
teoria-engine supports Linux with NVIDIA GPUs using vLLM and macOS Apple Silicon using MLX. It enables local serving of LLMs to other agents and tools with model switching and observability.
teoria-engine provides runtime scripts for install, start, and stop orchestration. Install teoria-engine with the one-line installer, then run teoria-engine up to start the stack.
teoria-engine allows you to start, stop, and switch model profiles to adapt to different workloads (text, vision-language, lightweight). It enables local serving of LLMs to other agents and tools.
teoria-engine uses Docker for orchestration and provides runtime scripts for install, start, and stop orchestration. It launches and manages a production-grade self-hosted LLM inference stack locally, exposing an OpenAI-compatible API.
schpetRun Linux containers natively on macOS with Apple Silicon.
automatedigitalRun GGUF quantized LLM inference on CPUs, Apple Silicon, and AMD/Intel GPUs.
constructive-ioCreate and manage pgvector databases in PostgreSQL with Ollama for RAG pipelines.
datathingsReference the llama.cpp C API for model loading and inference workflows.
