neuroskill-llm

Run a local llama.cpp server for OpenAI-compatible chat and GGUF model management.

11|4|Updated Mar 3, 2026

Search Tags:#llm #websocket #tool-calling #model-management #http-api #streaming-chat #llama.cpp

Ready to run

npx skills add https://github.com/NeuroSkill-com/skills --skill neuroskill-llm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: neuroskill-llm
Source: https://github.com/NeuroSkill-com/skills/tree/main/skills/neuroskill-llm
Command: npx skills add https://github.com/NeuroSkill-com/skills --skill neuroskill-llm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The built-in NeuroSkill LLM server removes dependency on remote APIs by running llama.cpp locally so you can chat, manage models, and execute tools without exposing private data.

Core Features & Use Cases

Server Lifecycle Control: Monitor status, start and stop inference, and view logs across CLI, WebSocket, and HTTP interfaces.
Model & Vision Management: Catalog, download, select, pause, resume, and delete GGUF models plus mmproj vision projectors with deployment-ready safeguards.
Interactive Usage: Stream multi-turn chat, single-shot prompts, automated tool calling, and persistent history while visualizing EEG signals, tool outputs, and hardware status.

Quick Start

Start the llm server, load a model, and ask it to explain EEG frequency bands.

Frequently Asked Questions about neuroskill-llm

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

FAQPage Schema

How do I run a local llama.cpp inference server without external APIs?▼

You can run a local llama.cpp inference server without external APIs by managing the server lifecycle, loading GGUF models, and accessing OpenAI-compatible chat through CLI, WebSocket, or HTTP endpoints.

Can I manage GGUF models and vision projectors locally?▼

You can manage GGUF models and vision projectors locally by cataloging, downloading, selecting, pausing, resuming, and deleting them with deployment-ready safeguards.

Does local llama.cpp support streaming chat and automatic tool calling?▼

Local llama.cpp supports streaming chat and automatic tool calling, allowing you to run multi-turn chat, single-shot prompts, and tune GenParams while maintaining persistent session history.

What is the best way to monitor local LLM server status and hardware usage?▼

The best way to monitor local LLM server status and hardware usage is by viewing logs and hardware status reporting interfaces during inference to ensure stable operation.

Do I need remote API keys to use OpenAI-compatible chat with local models?▼

You do not need remote API keys to use OpenAI-compatible chat with local models because the server runs llama.cpp locally to keep data private and execute tools independently.