Jan - Bring AI to your Desktop

Getting Started - Docs - Changelog - Bug reports - Discord

⚠️ Jan is currently in Development: Expect breaking changes and bugs!

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

Jan runs on any hardware. From PCs to multi-GPU clusters, Jan supports universal architectures:

• Nvidia GPUs (fast)
• Apple M-series (fast)
• Apple Intel
• Linux Debian
• Windows x64

Download

Version Type	Windows	MacOS		Linux
Stable (Recommended)	jan.exe	Intel	M1/M2	jan.deb	jan.AppImage
Experimental (Nightly Build)	jan.exe	Intel	M1/M2	jan.deb	jan.AppImage

Download the latest version of Jan at https://jan.ai/ or visit the GitHub Releases to download any previous release.

Demo

Realtime Video: Jan v0.4.3-nightly on a Mac M1, 16GB Sonoma 14

Quicklinks

Jan

• Jan website
• Jan GitHub
• User Guides
• Developer docs
• API reference
• Specs

Nitro

Nitro is a high-efficiency C++ inference engine for edge computing. It is lightweight and embeddable, and can be used on its own within your own projects.

• Nitro Website
• Nitro GitHub
• Documentation
• API Reference

Troubleshooting

As Jan is in development mode, you might get stuck on a broken build.

To reset your installation:

1. Use the following commands to remove any dangling backend processes:

   ps aux | grep nitro

   Look for processes like "nitro" and "nitro_arm_64," and kill them one by one with:

   kill -9 <PID>

2. Remove Jan from your Applications folder and Cache folder

   make clean

   This will remove all build artifacts and cached files:

   • Delete Jan extension from your ~/jan/extensions folder
   • Delete all node_modules in current folder
   • Clear Application cache in ~/Library/Caches/jan

Requirements for running Jan

• MacOS: 13 or higher
• Windows:
  • Windows 10 or higher
  • To enable GPU support:
    • Nvidia GPU with CUDA Toolkit 11.7 or higher
    • Nvidia driver 470.63.01 or higher
• Linux:
  • glibc 2.27 or higher (check with ldd --version)
  • gcc 11, g++ 11, cpp 11 or higher, refer to this link for more information
  • To enable GPU support:
    • Nvidia GPU with CUDA Toolkit 11.7 or higher
    • Nvidia driver 470.63.01 or higher

Contributing

Contributions are welcome! Please read the CONTRIBUTING.md file

Pre-requisites

• node >= 20.0.0
• yarn >= 1.22.0
• make >= 3.81

Instructions

1. Clone the repository and prepare:

   git clone https://github.com/janhq/jan
   cd jan
   git checkout -b DESIRED_BRANCH

2. Run development and use Jan Desktop

   make dev

This will start the development server and open the desktop app.

For production build

# Do steps 1 and 2 in the previous section
# Build the app
make build

This will build the app MacOS m1/m2 for production (with code signing already done) and put the result in dist folder.

Docker mode

• Supported OS: Linux, WSL2 Docker

• Pre-requisites:

  • docker and docker compose, follow instruction here

    curl -fsSL https://get.docker.com -o get-docker.sh
    sudo sh ./get-docker.sh --dry-run

  • nvidia-driver and nvidia-docker2, follow instruction here (If you want to run with GPU mode)

• Run Jan in Docker mode

  • Option 1: Run Jan in CPU mode

    docker compose --profile cpu up -d

  • Option 2: Run Jan in GPU mode

    • Step 1: Check cuda compatibility with your nvidia driver by running nvidia-smi and check the cuda version in the output

      nvidia-smi
      
      # Output
      +---------------------------------------------------------------------------------------+
      | NVIDIA-SMI 531.18                 Driver Version: 531.18       CUDA Version: 12.1     |
      |-----------------------------------------+----------------------+----------------------+
      | GPU  Name                      TCC/WDDM | Bus-Id        Disp.A | Volatile Uncorr. ECC |
      | Fan  Temp  Perf            Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
      |                                         |                      |               MIG M. |
      |=========================================+======================+======================|
      |   0  NVIDIA GeForce RTX 4070 Ti    WDDM | 00000000:01:00.0  On |                  N/A |
      |  0%   44C    P8               16W / 285W|   1481MiB / 12282MiB |      2%      Default |
      |                                         |                      |                  N/A |
      +-----------------------------------------+----------------------+----------------------+
      |   1  NVIDIA GeForce GTX 1660 Ti    WDDM | 00000000:02:00.0 Off |                  N/A |
      |  0%   49C    P8               14W / 120W|      0MiB /  6144MiB |      0%      Default |
      |                                         |                      |                  N/A |
      +-----------------------------------------+----------------------+----------------------+
      |   2  NVIDIA GeForce GTX 1660 Ti    WDDM | 00000000:05:00.0 Off |                  N/A |
      | 29%   38C    P8               11W / 120W|      0MiB /  6144MiB |      0%      Default |
      |                                         |                      |                  N/A |
      +-----------------------------------------+----------------------+----------------------+
      
      +---------------------------------------------------------------------------------------+
      | Processes:                                                                            |
      |  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
      |        ID   ID                                                             Usage      |
      |=======================================================================================|

    • Step 2: Go to https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda/tags and find the smallest minor version of image tag that matches the cuda version from the output of nvidia-smi (e.g. 12.1 -> 12.1.0)

    • Step 3: Update the Dockerfile.gpu line number 5 with the latest minor version of the image tag from step 2 (e.g. change FROM nvidia/cuda:12.2.0-runtime-ubuntu22.04 AS base to FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04 AS base)

    • Step 4: Run command to start Jan in GPU mode

      # GPU mode
      docker compose --profile gpu up -d

  This will start the web server and you can access Jan at http://localhost:3000.

  Note: Currently, Docker mode is only work for development and localhost, production is not supported yet. RAG feature is not supported in Docker mode yet.

Acknowledgements

Jan builds on top of other open-source projects:

• llama.cpp
• TensorRT

Contact

• Bugs & requests: file a GitHub ticket
• For discussion: join our Discord here
• For business inquiries: email [email protected]
• For jobs: please email [email protected]

License

Jan is free and open source, under the AGPLv3 license.