cuyamaca-llm-abstraction

Configure two-slot LLM backends with secure API-key storage and health checks.

Updated Mar 31, 2026

Search Tags:#llm #runtime #rust #tauri #multi-provider #code-model #dual-slot

Ready to run

npx skills add https://github.com/yuyanghu06/cuyamaca --skill cuyamaca-llm-abstraction

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: cuyamaca-llm-abstraction
Source: https://github.com/yuyanghu06/cuyamaca/tree/main/.claude/skills/cuyamaca-llm-abstraction
Command: npx skills add https://github.com/yuyanghu06/cuyamaca --skill cuyamaca-llm-abstraction

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill builds an architecture to manage two independent LLM slots (code model for sketch generation and runtime model for live control) across multiple providers, enabling flexible deployment and experimentation.

Core Features & Use Cases

Two-slot model manager: separate code-generation and runtime inference paths with configurable providers.
Provider agnosticism: supports Ollama, OpenAI, Anthropic, Google, and Mistral with secure API-key handling via OS keychain.
Model health & discovery: commands to list models, verify provider health, and validate slot configurations for safe operation.

Quick Start

Configure the code model slot to use Ollama llama3.2 and the runtime slot to use a multimodal provider, then verify health.

Frequently Asked Questions about cuyamaca-llm-abstraction

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I manage multiple LLM providers for different tasks like code generation and runtime control?▼

To manage multiple LLM providers, you can use a dual-slot architecture that separates code generation from runtime control, allowing you to configure distinct providers like Ollama or OpenAI for each specific inference task.

How do I securely store API keys when coordinating multiple LLM providers?▼

To securely store API keys when coordinating multiple LLM providers, you can utilize the OS keychain workflow, which safely manages credentials for services like Anthropic, Google, and Mistral without exposing them in your configuration files.

Can I use a non-multimodal model for runtime control in a dual-slot LLM setup?▼

You cannot use a non-multimodal model for runtime control, because the dual-slot architecture enforces multimodal capability checks specifically for the runtime slot to ensure safe and versatile live operation.

What is the best way to verify LLM provider health and validate slot configurations?▼

The best way to verify LLM provider health and validate slot configurations is by running built-in discovery and health-check commands, which confirm that your code and runtime model paths are operating safely.

Does this multi-provider LLM abstraction require specific dependencies to run locally?▼

Running this multi-provider LLM abstraction requires no specific external dependencies, allowing you to directly integrate the model manager and provider traits into your Rust or Tauri environment for flexible deployment.

Why do I need separate slots for code generation and runtime inference?▼

You need separate slots for code generation and runtime inference to isolate sketch generation from live control, enabling independent provider configuration, flexible experimentation, and optimized deployment for each specific task.