Vibe Coding DiscoverETOS-LLM-Studio
View on GitHubA 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.
Native iOS/watchOS LLM client in Swift: runs local GGUF models offline via llama.cpp or connects to OpenAI, Claude and Gemini. Adds session-level Chat/Agent modes, MCP tools, Agent Skills, an embedded Alpine Linux sandbox, Browser Agent, local SQLite RAG memory and two-way device sync.
Use Cases
Chat with cloud or local GGUF LLMs on iPhone and Apple WatchOffline on-device inference via llama.cpp with LoRA adaptersLocal RAG memory with SQLite vector store and embeddingsCalling MCP servers over Streamable HTTP/SSE and stdioAgent mode with Browser Agent (WKWebView) automationRunning Agent Skills scripts in a bundled Alpine Linux sandboxUsing 64 Apple-native device tools (HealthKit, HomeKit, etc.)Voice input (SFSpeechRecognizer) and TTS readoutSillyTavern-style worldbook / lorebook character promptsCross-device iOS↔watchOS session and config sync via CloudKitDaily Pulse proactive information cards with feedback learningSiri Shortcuts integration for AI actions
Built With
- Language
- Swift
- Frameworks
- SwiftUI · GRDB · SQLite · SQLCipher · llama.cpp · MCP Swift SDK · CloudKit · WatchConnectivity · Shortcuts · ActivityKit · WidgetKit · SwiftMath · ZIPFoundation · Swift Package Manager · CMake · Meson
Tags
ios · watchos · swift · swiftui · local-llm · llama.cpp · gguf · offline-inference · mcp · rag · agent · siri-shortcuts · on-device-embeddings · multimodal · speech · cross-device-sync