Jan is a desktop AI chat app built for people who want the capabilities of ChatGPT without handing their conversations to a cloud service. It runs entirely on your own machine using open-source models, or you can connect it to hosted providers when you need more power. Either way, you stay in control.

The model selection is broad. Out of the box, Jan supports:

• Local models like Llama, Mistral, Qwen, Gemma, and DeepSeek, downloaded and run on your hardware
• Cloud providers including OpenAI, Anthropic (Claude), Google (Gemini), and others, connected via API key
• Switching between them without leaving the app, so you're not locked into one backend

This flexibility is what separates Jan from simpler local-model runners. You get offline capability when you want privacy, and cloud fallback when a task demands it.

Jan is built in public and has crossed 5.7 million downloads, which puts it among the more widely adopted self-hosted AI interfaces alongside tools like Open WebUI and LibreChat. The codebase is open, community-driven, and free.

The interface is clean and focused on conversation. A memory feature is in development that will carry context and preferences across sessions, so you won't need to re-explain your setup or working style each time you start a new chat.

It's a practical fit for developers, designers, researchers, or anyone who handles sensitive work and doesn't want that data leaving their machine. Local inference does require reasonable hardware, but Jan handles model management inside the app, so you don't need to touch a terminal to get started.