llama-assistant

Why we included this project

Llama Assistant is a desktop assistant that runs entirely on your machine, so your questions and documents never leave it. It puts several open models behind one voice-driven interface: Llama 3.2 and DeepSeek R1 for text, plus vision models like LLaVA and Moondream for images. You can talk to it, ask it to summarize or rephrase text, draft emails, and handle routine tasks without an internet connection. The multimodal and RAG support stretch it beyond plain chat, which makes it a solid base for anyone who wants a private, self-contained assistant instead of another cloud subscription. It is also a good starting point for developers who want to extend it with their own models and workflows.