Etos LLM Studio
A powerful native LLM client for iOS & Apple Watch. Supports OpenAI/Claude/Gemini, featuring local RAG memory, Model Context Protocol (MCP) tools, Siri Shortcuts, and cross-device sync. Built with Swift.
What is Etos LLM Studio?
Etos LLM Studio is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to powerful native llm client for ios & apple watch. supports openai/claude/gemini, featuring local rag memory, model context protocol (mcp) tools, siri shortcuts, and cross-device sync. built with swift...
A powerful native LLM client for iOS & Apple Watch. Supports OpenAI/Claude/Gemini, featuring local RAG memory, Model Context Protocol (MCP) tools, Siri Shortcuts, and cross-device sync. Built with Swift.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A powerful native LLM client for iOS & Apple Watch. Supports
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx etos-llm-studioConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Etos LLM Studio
ETOS LLM Studio is a native iOS and Apple Watch AI client built in Swift that supports OpenAI, Anthropic Claude, and Google Gemini cloud models alongside local GGUF models via llama.cpp. It integrates the Model Context Protocol using the official Swift SDK, allowing users to connect external MCP servers for tool use directly from their iPhone or Apple Watch. The app includes local RAG memory with SQLite-based vector storage, a Daily Pulse briefing system, and cross-device iCloud synchronization, making it a full-featured AI assistant platform for Apple devices.
Prerequisites
- An iPhone running iOS 17 or later (or Apple Watch with paired iPhone)
- Xcode 15 or later if building from source (macOS required)
- API keys for the cloud models you want to use: OpenAI, Anthropic, and/or Google Gemini
- For local models: GGUF-format model weights compatible with llama.cpp
- MCP server endpoints (HTTP/SSE URLs) for any external tools you want to connect
Install ETOS LLM Studio on your iPhone
Get the app from the App Store (a symbolic purchase fee supports development) or join the TestFlight beta for the latest features. Alternatively, build from source using Xcode.
Add a cloud model provider
Open the app and navigate to Settings > Providers. Add your API key for OpenAI, Anthropic Claude, or Google Gemini. Each provider can be enabled or disabled per chat.
Add a local GGUF model (optional)
To run models fully on-device, import a GGUF-format weight file (e.g. a Llama or Mistral quantised model). The app bridges these through llama.cpp's C API and exposes controls for context length, GPU layers, and sampling parameters.
Connect an MCP server for tool use
In Settings > MCP Servers, add a remote MCP server URL using Streamable HTTP or SSE transport. The app supports automatic reconnection and metadata refresh. Per-chat visibility toggles let you enable only the tools relevant to a conversation.
Enable local RAG memory
Turn on Local Memory in Settings to enable SQLite-backed vector storage. The app will automatically index your conversation history and surface relevant context in future chats.
Configure Daily Pulse
Daily Pulse generates an intelligent morning briefing card with information you care about. Set up your topics of interest in the Daily Pulse settings and it will pull summaries each morning.
Etos LLM Studio Examples
Client configuration
ETOS LLM Studio is a standalone iOS app — there is no JSON config file. MCP servers are added via the in-app settings UI. A typical MCP server endpoint looks like the following.
{
"name": "My MCP Server",
"transport": "streamable-http",
"url": "https://your-mcp-server.example.com/mcp",
"approvalPolicy": "ask"
}Prompts to try
Use ETOS LLM Studio to interact with AI models and connected MCP tools from your iPhone or Apple Watch.
- "Summarize my meetings from today using the calendar MCP tool"
- "Use the file search tool to find documents about Q4 planning"
- "Give me a brief daily briefing about AI news"
- "Translate this text to Spanish and save it to my notes"
- "Search the web for the latest news on Swift 6 concurrency"Troubleshooting Etos LLM Studio
MCP server fails to connect or tools are not appearing
Verify the server URL is reachable from your iPhone's network (not localhost unless using a local network address). Check that the server supports Streamable HTTP or SSE transport, and toggle the server off and on in Settings to trigger a reconnect.
Local GGUF model is slow or crashes
Reduce the number of GPU layers in the model settings if the Metal GPU runs out of memory. Try a smaller quantization (e.g. Q4_K_M instead of Q8) to reduce memory footprint.
Build from source fails in Xcode
Ensure you have Xcode 15 or later and have accepted the license (sudo xcodebuild -license). Run a clean build (Product > Clean Build Folder) before retrying. Check that the Swift package dependencies have resolved successfully.
Frequently Asked Questions about Etos LLM Studio
What is Etos LLM Studio?
Etos LLM Studio is a Model Context Protocol (MCP) server that powerful native llm client for ios & apple watch. supports openai/claude/gemini, featuring local rag memory, model context protocol (mcp) tools, siri shortcuts, and cross-device sync. built with swift. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Etos LLM Studio?
Follow the installation instructions on the Etos LLM Studio GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Etos LLM Studio?
Etos LLM Studio works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Etos LLM Studio free to use?
Yes, Etos LLM Studio is open source and available under the GPL-3.0 license. You can use it freely in both personal and commercial projects.
Etos LLM Studio Alternatives — Similar Cloud Services Servers
Looking for alternatives to Etos LLM Studio? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Etos LLM Studio in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Etos LLM Studio?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.