Jan

Jan is an open-source, local-first AI desktop application designed to facilitate the deployment and management of large language models (LLLLMs) on personal hardware. The platform provides a centralized interface for downloading, configuring, and interacting with various models, supporting a wide range of architectures through integrated tools like llama.cpp and TensorRT-LLM. By leveraging local computation, Jan enables users to run AI models entirely offline, ensuring data privacy and security by eliminating the need for external API calls. The application architecture supports extensible plugin systems and provides advanced configuration options for hardware acceleration, allowing users to optimize performance across different CPU and GPU environments.