ETOS LLM Studio
A native AI and agent client for iOS and Apple Watch that connects to OpenAI, Anthropic Claude and Google Gemini, or runs local GGUF models offline through llama.cpp, with local RAG and MCP tools.
ETOS LLM Studio is a native Swift client for iOS and Apple Watch that manages both cloud model providers (OpenAI, Anthropic, Google) and local GGUF weights run through an embedded llama.cpp bridge, with per-model sampling, context length, LoRA adapters and chat template controls. Sessions support folders, tags, full-text search, and message-level regex rewrite rules, and can be synchronized between the phone and the watch.
An agent mode can operate a controlled browser, call Apple's native capabilities, or run shell commands and skill scripts inside a bundled local Linux environment, and supports local Model Context Protocol tools. It also offers on-device speech-to-text and text-to-speech, session import from other chat apps, and export to PDF, Markdown or plain text.