janhq/jan

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

What it solves

Jan provides a privacy-focused, open-source alternative to ChatGPT that allows users to run large language models (LLMs) locally on their own hardware or connect to cloud-based AI services, giving them full control over their data and model choice.

How it works

Jan is a desktop application built with Tauri and powered by llama.cpp. It enables users to download and run open-source models (such as Llama, Gemma, and Qwen) directly from HuggingFace. It also supports integration with cloud APIs from providers like OpenAI, Anthropic, and Groq. For developers, it hosts a local OpenAI-compatible API server at localhost:1337 and supports the Model Context Protocol (MCP) for agentic capabilities.

Who it’s for

It is designed for users who want a user-friendly interface for interacting with AI models while maintaining privacy, as well as developers who need a local AI server for other applications.

Highlights

  • Local Model Execution: Run LLMs locally to ensure data privacy.
  • Cloud Integration: Connect to various external AI providers including OpenAI and Claude.
  • Custom Assistants: Create specialized AI assistants tailored to specific tasks.
  • OpenAI-Compatible API: Provides a local server for seamless integration with other tools.
  • MCP Support: Integration with the Model Context Protocol for agentic features.

Related

  • Project
    Mobile-Artificial-Intelligence/maid

    An open-source Android application for interacting with LLMs locally via llama.cpp or remotely through various AI providers.

  • Project
    ServiceStack/llms

    A lightweight CLI, API, and web interface for accessing multiple LLMs privately, with all data stored locally in the browser.

  • Project
    google-ai-edge/gallery

    A mobile and macOS application for running open-source LLMs locally on-device, providing a private and offline environment to experience and evaluate generative AI.

  • Project
    huggingface/chat-ui

    A SvelteKit-based chat interface for LLMs that connects to OpenAI-compatible APIs, featuring smart routing, MCP tool support, and MongoDB persistence.

  • Project
    AtomicBot-ai/Atomic-Chat

    A local AI application and inference engine that lets users run open-weight LLMs privately on their own devices while providing an OpenAI-compatible API for other agents.