Skip to content

Desktop

Jan Desktop is your local AI workstation. Download it, run your own models, or connect to cloud providers. Your computer, your choice.

How It Works

Default: Local Mode

Open Jan. Start chatting with Jan Nano. No internet, no account, no API keys. Your conversations never leave your machine.

Optional: Cloud Mode

Need more power? Connect to:

  • Your own Jan Server
  • jan.ai (coming soon)
  • Any OpenAI-compatible API

Why Desktop First

Your desktop has the GPU, storage, and memory to run real AI models. Not toy versions. Not demos. The same models that power ChatGPT-scale applications.

More importantly: it becomes the hub for your other devices. Your phone connects to your desktop. Your team connects to your desktop. Everything stays in your control.

Specifications

Storage

Everything in ~/.local/share/jan. Your data, your models, your configuration. Back it up, move it, delete it - it’s just files.

API Server

OpenAI-compatible API at localhost:1337. Any tool that works with OpenAI works with Jan. No code changes.

GPU Support

NVIDIA CUDA acceleration out of the box. Automatically detects and uses available GPUs. CPU fallback always works.

Model Flexibility

Run any GGUF model from Hugging Face. Or our models. Or your fine-tuned models. If it’s GGUF, it runs.

System Requirements

Minimum: 8GB RAM, 10GB storage, any 64-bit OS from the last 5 years

Recommended: 16GB RAM, NVIDIA GPU, 50GB storage for multiple models

Runs on: Windows 10+, macOS 12+, Ubuntu 20.04+

Installation

Terminal window
# macOS/Linux
curl -sSL https://jan.ai/install.sh | bash


# Windows
# Download from jan.ai/download

For Developers

Use Jan as an OpenAI Drop-in

// Your existing OpenAI code
const openai = new OpenAI({
  apiKey: "not-needed",
  baseURL: "http://localhost:1337/v1"
});


// Works exactly the same
const completion = await openai.chat.completions.create({
  model: "jan-nano",
  messages: [{ role: "user", content: "Hello" }]
});

Available Endpoints

  • /v1/chat/completions - Chat with any loaded model
  • /v1/models - List available models
  • /v1/embeddings - Generate embeddings
  • /routes - See all available routes

The Foundation

Jan Desktop isn’t just an app. It’s the foundation of your personal AI infrastructure:

  1. Today: Run models locally, connect to cloud APIs
  2. Soon: Your phone connects to your desktop
  3. Next: Your desktop serves your team
  4. Future: Your personal AI that knows you, runs everywhere

No subscriptions. No lock-in. Just software that’s yours.

Next steps: