Jan

Founded by Ngoc Nguyen in 2023

Run open-source language models locally or connect to external cloud models privately

Pricing model

Free

Rating

★ People love it

Time to value

Quick Setup (< 1 hour)

You can use Jan to run open-source language models directly on your computer without sending your data to remote servers. It functions as an offline desktop assistant that lets you download models like Llama, Mistral, and DeepSeek, or connect existing API keys for cloud providers like OpenAI, Claude, and Gemini. You can easily switch between different models during chats, adjust hardware settings, manage custom preferences, and maintain full control over your conversation history and private context on your own device.

What Jan does

Download and run open-source models locallySwitch between local and cloud model providersConnect external API keys for OpenAI and AnthropicConfigure context length and generation parametersOrganize and search local conversation historiesSet custom instructions and system prompt behaviorsRuns language models locally on your computer hardwareConnects to cloud providers like OpenAI, Anthropic, and Google via API keysMaintains chat history and user context directly on local storageDownloads pre-configured open-source models with a single clickOperates completely offline without an active internet connectionCustomizes system prompts and memory preferences across conversations