> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/janhq/jan/llms.txt
> Use this file to discover all available pages before exploring further.

# Jan - Open-Source ChatGPT Alternative

> Run AI models 100% offline on your computer with full privacy and control. Jan is an open-source alternative to ChatGPT.

# Welcome to Jan

Jan is bringing the best of open-source AI in an easy-to-use product. Download and run LLMs with **full control** and **privacy**.

<CardGroup cols={2}>
  <Card title="Download Jan" icon="download" href="/quickstart">
    Get started in under 5 minutes. Download, install, and chat with AI models locally.
  </Card>

  <Card title="Installation Guide" icon="gear" href="/installation">
    Platform-specific instructions for Windows, macOS, and Linux.
  </Card>

  <Card title="Model Context Protocol" icon="puzzle" href="https://jan.ai/docs/desktop/mcp">
    Enable agentic capabilities with MCP integration for web search, productivity tools, and more.
  </Card>

  <Card title="API Reference" icon="code" href="https://jan.ai/api-reference">
    OpenAI-compatible local API server at localhost:1337 for integrations.
  </Card>
</CardGroup>

## Why Jan?

Jan combines the power of open-source AI with privacy-first principles, giving you a ChatGPT-like experience that runs entirely on your machine.

<CardGroup cols={3}>
  <Card title="100% Offline" icon="shield">
    Everything runs locally when you want it to. Your data never leaves your computer.
  </Card>

  <Card title="Local AI Models" icon="brain">
    Download and run Llama, Gemma, Qwen, GPT-oss, and more from HuggingFace.
  </Card>

  <Card title="Cloud Integration" icon="cloud">
    Connect to GPT (OpenAI), Claude (Anthropic), Mistral, Groq, and other cloud models.
  </Card>

  <Card title="Custom Assistants" icon="robot">
    Create specialized AI assistants tailored to your specific tasks and workflows.
  </Card>

  <Card title="OpenAI-Compatible API" icon="plug">
    Local server at localhost:1337 lets other applications integrate with your models.
  </Card>

  <Card title="Free & Open Source" icon="code-branch">
    Apache 2.0 licensed. Inspect the code, contribute, or build your own extensions.
  </Card>
</CardGroup>

## Key Features

### Local AI Models

Download and run large language models from HuggingFace directly on your machine:

* Llama 3.1, 3.2, 3.3
* Gemma 2
* Qwen 2.5
* GPT-oss
* Jan v1 (4B parameter model optimized for reasoning)
* And hundreds more

### Cloud Model Support

Connect to leading cloud AI providers:

* **OpenAI**: GPT-4, GPT-4 Turbo, GPT-3.5
* **Anthropic**: Claude 3.5 Sonnet, Claude 3 Opus
* **Mistral AI**: Mistral Large, Mistral Medium
* **Groq**: Ultra-fast inference
* **Cohere**: Command models
* **Google**: Gemini models

### Model Context Protocol (MCP)

Extend Jan's capabilities with agentic features:

* Web search integration (Serper, Exa)
* Productivity tools (Linear, Todoist)
* Data analysis (Jupyter, E2B)
* Design tools (Canva)
* And more community servers

### Privacy First

When running local models:

* No internet connection required
* No data collection
* No telemetry
* Complete offline operation
* Full control over your data

## System Requirements

<Tabs items={["Minimum", "Recommended"]}>
  <Tab>
    **Operating System**

    * macOS 13.6+
    * Windows 10+
    * Linux (most distributions)

    **Memory**

    * 8GB RAM (3B parameter models)
    * 10GB free disk space

    **Processor**

    * CPU with AVX2 support
    * Intel Haswell (2013) or newer
    * AMD Excavator (2015) or newer
  </Tab>

  <Tab>
    **For Best Performance**

    * 16-32GB RAM (7B-13B models)
    * NVIDIA GPU with 8GB+ VRAM
    * AMD or Intel Arc GPU with 8GB+ VRAM
    * Apple Silicon (M1/M2/M3) for Mac users

    **GPU Acceleration**

    * NVIDIA: CUDA 11.7+ support
    * AMD/Intel: Vulkan support
    * Apple: Metal acceleration (built-in)
  </Tab>
</Tabs>

<Note>
  Larger models require more RAM and VRAM. A 7B parameter model typically needs 16GB RAM or 8GB VRAM for smooth operation.
</Note>

## Quick Example

Once installed, using Jan is as simple as:

<Steps>
  <Step title="Download a Model">
    Browse the Hub tab and download Jan v1 (2.5GB) or any model from HuggingFace.
  </Step>

  <Step title="Start Chatting">
    Click "New Chat", select your model, and start asking questions.
  </Step>

  <Step title="Customize (Optional)">
    Create custom assistants, adjust model parameters, or enable MCP tools for enhanced capabilities.
  </Step>
</Steps>

## Popular Use Cases

<CardGroup cols={2}>
  <Card title="Code Assistant" icon="code">
    Use models like Qwen Coder or GPT-4 to help with programming tasks, debugging, and code reviews.
  </Card>

  <Card title="Research & Writing" icon="book">
    Run DeepSeek R1 or Claude for in-depth research, content creation, and document analysis.
  </Card>

  <Card title="Privacy-Sensitive Work" icon="lock">
    Process confidential data locally without cloud exposure - perfect for legal, medical, or financial work.
  </Card>

  <Card title="Development & Testing" icon="flask">
    Use the local API server (localhost:1337) to build and test AI-powered applications.
  </Card>
</CardGroup>

## Architecture

Jan is built on proven open-source technologies:

* **[llama.cpp](https://github.com/ggerganov/llama.cpp)**: Efficient inference engine for LLMs
* **[Tauri](https://tauri.app/)**: Lightweight cross-platform desktop framework
* **Model Context Protocol**: Standard for AI agent integration
* **OpenAI-compatible API**: Industry-standard API format

## Community & Support

<CardGroup cols={2}>
  <Card title="Discord Community" icon="discord" href="https://discord.gg/FTk2MvZwJH">
    Join 30,000+ users in our Discord server. Get help in #🆘|jan-help channel.
  </Card>

  <Card title="GitHub" icon="github" href="https://github.com/janhq/jan">
    Report issues, contribute code, or star the repo.
  </Card>

  <Card title="Changelog" icon="list" href="https://jan.ai/changelog">
    See what's new in each release.
  </Card>

  <Card title="Documentation" icon="book-open" href="https://jan.ai/docs">
    Comprehensive guides and API documentation.
  </Card>
</CardGroup>

<Info>
  Ready to get started? Head to the [Quickstart Guide](/quickstart) to download Jan and run your first AI model in minutes.
</Info>

## Next Steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Install Jan and start your first chat in under 5 minutes.
  </Card>

  <Card title="Installation" icon="download" href="/installation">
    Platform-specific installation instructions and GPU setup.
  </Card>
</CardGroup>