Skills
.Work. You
Rest

teoria-engine

Community

Run a private OpenAI-compatible LLM locally

Software Engineering#llm#orchestration#docker#macos#linux#gateway#local-inference
Authorjgabriellima
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Starts, uses, and stops a production-grade self-hosted LLM inference stack, providing a private OpenAI-compatible API endpoint for local AI workloads.

Core Features & Use Cases

  • Self-hosted OpenAI-compatible API gateway and stack with Linux + NVIDIA GPU backends (vLLM) or macOS MLX.
  • Start, stop, and switch model profiles to adapt to different workloads (text, vision-language, lightweight).
  • Observability and secure local serving to other agents and tools without exposing external endpoints.

Quick Start

Install teoria-engine with the one-line installer, then run teoria-engine up to start the stack.

Dependency Matrix

Required Modules

None required

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: teoria-engine
Download link: https://github.com/jgabriellima/teoria-engine/archive/main.zip#teoria-engine

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.