skills.rest
sliamh11
sliamh11COMMUNITY
Explore all skills by this author →
GitHub

add-llama-cpp

Install and verify a local llama.cpp server for Deus local-generation experiments.

50|4|Updated Mar 21, 2026
Search Tags:#macos#llama.cpp#local-generation#llama-server#deus#host-install
One-click install
npx skills add https://github.com/sliamh11/Deus --skill add-llama-cpp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-llama-cpp
Source: https://github.com/sliamh11/Deus/tree/main/.claude/skills/add-llama-cpp
Command: npx skills add https://github.com/sliamh11/Deus --skill add-llama-cpp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Install and verify a local llama.cpp server to enable optional Deus local-generation experiments, while Ollama remains the default for embeddings and judge work.

Core Features & Use Cases

  • Install llama.cpp and run llama-server as a local host service for Deus local-generation experiments.
  • Wire the local endpoint into Deus when the current checkout supports the optional llama_cpp provider integration.
  • Ensure Ollama remains available for embeddings and judging by default, preserving workflow continuity.

Quick Start

Install llama.cpp, configure the local service, and verify the endpoint to start using local generation.

Frequently Asked Questions about add-llama-cpp

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

FAQPage Schema
How do I install and run a local llama.cpp server on macOS?▼

You can use a local llama.cpp server with Linux or Windows, but manual configuration paths are required. The setup is primarily macOS-focused, requiring a host installation of llama-server and a configured environment file to connect properly.

How do I install and run a local llama.cpp server on macOS?▼

To install a local llama.cpp server on macOS, you need to set up a host installation of llama-server, configure your environment file, and wire the local endpoint into your Deus checkout. This enables optional local-generation experiments.

Why run llama-server for Deus local-generation instead of using Ollama?▼

Running llama-server for Deus local-generation allows you to run experiments locally while keeping Ollama as the default provider for embeddings and judging tasks. This preserves your existing workflow continuity.

Does the llama.cpp local-generation setup work on Linux and Windows?▼

You can use a local llama.cpp server with Linux or Windows, but manual configuration paths are required. The setup is primarily macOS-focused, requiring a host installation of llama-server and a configured environment file to connect properly.

What do I need to verify before wiring llama-server into Deus?▼

Before wiring llama-server into Deus, verify that your current checkout includes the optional llama_cpp provider wiring and that your environment file is configured correctly. This ensures the local endpoint connects successfully.

What are the limitations of using llama.cpp for local generation?▼

The main limitation is that llama.cpp is strictly for optional local-generation experiments. It does not replace Ollama, which must remain available and default for handling embeddings and judging work to maintain workflow continuity.

Related Skills

Explore More Software Engineering Skills→
BartunekBartunek

add-opencode

Enable the OpenCode provider in NanoClaw with host and container wiring.

Community
Advanced
zengbaochengzengbaocheng

llama-cpp

Run local GGUF inference with llama.cpp using llama-server or llama-cli.

Community
Advanced
rawvegrawveg
40

ollama

Run and interact with local AI models via the Ollama API.

Community
Advanced
TencentBlueKingTencentBlueKing
839

bk-monitor-dev-server

Configure and start local development servers using pnpm dev workflows.

Official
Intermediate