About CuriousLM
Local AI with a visible boundary.
CuriousLM is a free, account-free workspace for running compatible AI models on your device, working with local files, and organising private projects.
What CuriousLM does
After a compatible model and required runtime components are available, normal chat inference runs on the device. Chats, projects, memories, imported files, indexes, and model artifacts are stored locally.
CuriousLM is designed for private everyday work, not only model demonstrations. It combines local generation with projects, source citations, file retrieval, temporary chats, deliberate model selection, and controls for local storage.
Read the complete product explanation for supported workflows, architecture, and device limitations.
What local does not mean
Local inference does not mean the application can never use a network. First load, model and runtime downloads, updates, optional Tavily web searches, user-confirmed response reports, and cookieless aggregate analytics can use the internet.
Normal chat content is not sent to a CuriousLM inference service. Actions that can send content outside the device are optional and presented for confirmation.
Who makes it
CuriousLM is created and published by Ebenezer Don. Product pages and guides use named authorship so readers can distinguish maintained CuriousLM material from anonymous or automatically assembled pages.
The guide library is written to explain trade-offs, not to claim that local AI is always the right tool. Device limits, setup requirements, online exceptions, and uncertain behaviour are included where they affect a decision.