LocalMind
A Flutter mobile app for iOS and Android that provides one chat interface for on-device LLMs and for local or cloud LLM servers such as LM Studio, Ollama and OpenRouter, with MCP tool support and a built-in model manager.
LocalMind connects to local inference servers such as LM Studio or Ollama as well as cloud providers such as OpenRouter or Requesty, and can also run GGUF and LiteRT models, including Gemma, Qwen and DeepSeek R1, directly on the device with no internet connection through llamadart and flutter_gemma. A model manager downloads curated models or pulls GGUF files directly from Hugging Face and manages them inside the app.
It connects to local or remote MCP servers with per-chat and global toggles, giving a connected model access to custom tools such as file access, web APIs or shell actions. The chat interface supports streaming responses, markdown rendering, collapsible reasoning logs for models like DeepSeek R1, editing and regenerating past prompts, saved message templates, message variants, an incognito mode that does not save history, and speech-to-text and text-to-speech.