[Gradient Open Sources Parallax, Driving Local AI Applications Forward] Odaily Planet Daily reports that the distributed AI lab Gradient has announced the open-sourcing of Parallax, an operating system designed for local AI applications. This system supports cross-platform and cross-regional deployment of open-source large models on heterogeneous devices such as Mac and Windows, enabling users to take control of models, data, and AI memory. Parallax features built-in network-aware sharding and dynamic task routing mechanisms, allowing intelligent scheduling based on inference loads and seamless switching between single-machine, multi-device, and wide-area cluster modes. Currently, Parallax is compatible with over 40 open-source large models, including Qwen3, Kimi K2, DeepSeek R1, and gpt-oss. Developers can deploy locally to fully build and run various AI applications such as programming assistants, personal agents, and multimodal generation, keeping sensitive data and control permissions entirely local.