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, ensuring full control over their data and privacy.

How it works

Jan is a desktop application that enables users to download and run open-source LLMs (such as Llama, Gemma, and Qwen) directly from HuggingFace. It also supports cloud-based models via integrations with providers like OpenAI, Anthropic, and Groq. The app includes a local server with an OpenAI-compatible API, allowing other applications to connect to it, and integrates the Model Context Protocol (MCP) for agentic capabilities.

Who it’s for

It is designed for users who want the convenience of a ChatGPT-like interface but prefer to run models locally for privacy, developers who need an OpenAI-compatible local API, and those who want to manage multiple local and cloud AI assistants.

Highlights

  • Local AI Execution: Run models from HuggingFace locally on Windows, macOS, and Linux.
  • Cloud Integration: Seamlessly switch between local models and cloud APIs (OpenAI, Claude, etc.).
  • Custom Assistants: Create specialized AI assistants for specific tasks.
  • OpenAI-Compatible API: Provides a local server at localhost:1337 for external app integration.
  • MCP Integration: Supports the Model Context Protocol for agentic capabilities.
  • Privacy First: Ensures data stays local when the user chooses local execution.

Related

  • Project
    ImDarkTom/LlamaPen

    A web-based GUI for Ollama and other local LLM providers that allows users to chat with self-hosted models via a privacy-focused interface.

  • Project
    ServiceStack/llms

    A lightweight, self‑hosted CLI/API tool that provides a ChatGPT‑like web UI for offline interaction with multiple local LLMs, with optional MCP integration and shareable conversation extensions.

  • Project
    addyosmani/chatty

    A private, in-browser AI chat interface that uses WebGPU to run LLMs locally on your hardware for offline use and data privacy.

  • Project
    chatboxai/chatbox

    Chatbox is a cross-platform desktop and mobile client that provides a unified interface for popular AI models like ChatGPT, Claude, and local LLMs. It simplifies AI access by offering a local-first, easy-to-install application with features for prompt management and team collaboration.

  • Project
    oobabooga/textgen

    A private, open-source desktop app for running local LLMs with support for multiple backends, multimodal input, tool-calling, and local fine-tuning.