Show HN: AnythingLLM Fork as NPM Package (github.com)

Totem LLM, an innovative fork of AnythingLLM, has been released as an NPM package, providing a sovereign AI solution optimized for consumer-grade hardware. This tool is designed to enhance user control over data privacy by allowing AI models to run locally on devices like laptops and desktops, minimizing reliance on cloud services. Users can effortlessly install it with a single command, which resolves all dependencies for a seamless setup. The significance of Totem LLM lies in its focus on privacy and local processing, catering to users wary of third-party data handling. It supports both local and cloud-based LLM providers, enabling users to opt for their preferred setup based on their needs. With a modular architecture, Totem LLM encourages the integration of additional features and models over time, enhancing its long-term usability. The initial model recommendation is qwen3.5:2b, with optimizations available for different hardware configurations, ensuring that users can choose a setup that fits their device capabilities.