by Eric-Terminal · MCP Server · ★ 146
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
ETOS LLM Studio 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 Русский 📸 截图 👋 写在前面 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 VitePress 文档站依赖算进来)的工程,它确实已经长大了不少。虽然名字叫 "ETOS LLM Studio" 听着有点唬人,但它本质上还是我拿来探索大模型应用边界的试验场。 现在它已经不只是一个手表端 App 了:我把 iOS 端也一点点补成了完整版本,方便在手机上管理云端模型、本地 GGUF 权重、工具、记忆、世界书和每日脉冲;两端数据还能通过内置同步引擎自动互通。 因为我平时主要还是用 Mac 和 Watch,iPhone 端偶尔会有一些还在继续打磨的边角,不过我会继续慢慢补齐。 主要功能 聊天与模型 双端原生体验:iOS 和 Apple Watch 原生适配,两端界面风格统一,但会针对不同屏幕尺寸分别优化交互;iOS 会话列表采用卡片样式,
| Stars | 146 |
| Forks | 9 |
| Language | Swift |
| Category | MCP Server |
| License | GPL-3.0 |
| Quality Score | 60.2380037253084/100 |
| Open Issues | 7 |
| Last Updated | 2026-06-28 |
| Created | 2025-09-06 |
| Platforms | claude-code, cli, gemini, mcp |
| Est. Tokens | ~18k |
These tools work well together with ETOS-LLM-Studio for enhanced workflows:
Looking for a ETOS-LLM-Studio alternative? If you're comparing ETOS-LLM-Studio with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Galway Bus Kotlin Multiplatform project using Jetpack Compose and SwiftUI
InferrLM - On-device AI for iOS & Android
MCP-NixOS - Model Context Protocol Server for NixOS resources
RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in differen
The most advanced, fully offline client-side AI suite on Android today.
Fantasy Premier League Kotlin/Compose Multiplatform sample
Explore other popular mcp server tools:
ETOS-LLM-Studio is 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 . It is categorized as a MCP Server with 146 GitHub stars.
ETOS-LLM-Studio is primarily written in Swift. It covers topics such as ai-assistant, apple-watch, daily-pulse.
You can find installation instructions and usage details in the ETOS-LLM-Studio GitHub repository at github.com/Eric-Terminal/ETOS-LLM-Studio. The project has 146 stars and 9 forks, indicating an active community.
ETOS-LLM-Studio is released under the GPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to ETOS-LLM-Studio on Agent Skills Hub include GalwayBus, InferrLM, mcp-nixos. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.