MCP Directory
Back

ETOS-LLM-Studio

by Eric-Terminal · Swift · ★ 146

A native LLM client for iOS & Apple Watch. Run local GGUF models offline via llama.cpp, or connect to OpenAI/Claude/Gemini. Features local RAG, Model Context Protocol (MCP) tools, Siri Shortcuts, and cross-device sync. Built with Swift.

#ai-assistant#apple-watch#daily-pulse#gguf#ios#llama-cpp#llm-client#mcp#rag#swiftui

Install

git clone https://github.com/Eric-Terminal/ETOS-LLM-Studio.git

Auto-generated from the repo's primary language — check the repo's own README for its exact install instructions.

Claude Desktop config

A starting point for your claude_desktop_config.json (auto-generated — the repo's README may specify a published package name or required env vars):

{
  "mcpServers": {
    "etos-llm-studio": {
      "command": "npx",
      "args": [
        "-y",
        "github:Eric-Terminal/ETOS-LLM-Studio"
      ]
    }
  }
}

From the README

**一个运行在 iOS 和 Apple Watch 上的原生 AI 客户端。支持 OpenAI、Anthropic Claude、Google Gemini 与本机 GGUF / llama.cpp 模型,内置 MCP 工具调用、Agent Skills 技能包、本地 RAG 记忆、世界书、每日脉冲、应用锁与 SQLCipher 全盘加密、CloudKit / WatchConnectivity 双端同步以及 Siri 快捷指令。** [English](docs/readme/README_EN.md) | [繁體中文](docs/readme/README_ZH_HANT.md) | [日本語](docs/readme/README_JA.md) | [Русский](docs/readme/README_RU.md) :|:---:| | | | --- 在学校的日子挺无聊的,平时又总会冒出很多想问 AI 的问题。当时我嫌 App Store 上的 AI 应用要么贵得离谱,要么功能太残废(尤其是手表端),索性就自己动手搓了一个。 从最初那个只有 1,800 行代码、API Key 还要硬编码的简陋版本,到现在 **641 个 Swift 源文件、226,381 行 Swift 代码**(仅计算项目内 Swift,不把 llama.cpp 子模块和 VitePr…
Read full README on GitHub →

Related ai & ml servers