Tinfoil Chat
Use a private AI chat workspace with temporary conversations and encrypted sync.
Run a private AI assistant on your own device

CuriousLM runs a language model on your own device so you can chat without sending the conversation to a hosted model service. Download a model once, then ask questions, draft text, or explore ideas offline. The interface can underline uncertain words and show alternative continuations, giving you a way to inspect how a response was generated without treating that display as a fact check. Voice features use additional local models, and optional offline Wikipedia content provides another source of information. Model files take up storage, and response speed depends on the device and model you choose. CuriousLM keeps the assistant and its settings close to the device where you use it.
Tried it? Share a useful thought or ask a question.
Good conversations start with a hello.
Sign in to comment