Repository files navigation

Getting Started -Docs -Changelog -Bug reports -Discord

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

Jan is a ChatGPT-alternative that runs 100% offline on your device. Our goal is to make it easy for a layperson to download and run LLMs and use AI withfull control andprivacy.

Jan is powered byCortex, our embeddable local AI engine that runs on any hardware.From PCs to multi-GPU clusters, Jan & Cortex supports universal architectures:

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

• Model Library with popular LLMs like Llama, Gemma, Mistral, or Qwen
• Connect toRemote AI APIs like Groq and OpenRouter
• Local API Server with OpenAI-equivalent API
• Extensions for customizing Jan

Version Type	Windows	MacOS Universal	Linux
Stable (Recommended)	jan.exe	jan.dmg	jan.deb	jan.AppImage
Beta (Preview)	jan.exe	jan.dmg	jan.deb	jan.AppImage
Nightly Build (Experimental)	jan.exe	jan.dmg	jan.deb	jan.AppImage

Download the latest version of Jan athttps://jan.ai/ or visit theGitHub Releases to download any previous release.

Real-time Video: Jan v0.5.7 on a Mac M2, 16GB Sonoma 14.2

• Jan Website
• Jan GitHub
• Documentation
• Jan Changelog
• Jan Blog

Jan is powered byCortex.cpp. It is a C++ command-line interface (CLI) designed as an alternative toOllama. By default, it runs on the llama.cpp engine but also supports other engines, including ONNX and TensorRT-LLM, making it a multi-engine platform.

• Cortex Website
• Cortex GitHub
• Documentation
• Models Library
• API Reference:Under development

• 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 withldd --version)
  • gcc 11, g++ 11, cpp 11 or higher, refer to thislink for more information
  • To enable GPU support:
    • Nvidia GPU with CUDA Toolkit 11.7 or higher
    • Nvidia driver 470.63.01 or higher

As Jan is in development mode, you might get stuck on a some common issues:

• Troubleshooting a broken build
• Troubleshooting NVIDIA GPU
• Troubleshooting Something's Amiss

If you can't find what you need in our troubleshooting guide, feel free reach out to us for extra help:

1. Copy yourerror logs & device specifications.
2. Go to ourDiscord & send it to#🆘|get-help channel for further support.

Check the logs to ensure the information is what you intend to send. Note that we retain your logs for only 24 hours, so report any issues promptly.

Contributions are welcome! Please read theCONTRIBUTING.md file

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

1. Clone the repository and prepare:

   git clone https://github.com/janhq/jancd jangit checkout -b DESIRED_BRANCH

2. Run development and use Jan Desktop

   make dev

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

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

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

Jan builds on top of other open-source projects:

• llama.cpp
• LangChain
• TensorRT
• TensorRT-LLM

• Bugs & requests: file a GitHub ticket
• For discussion: join our Discordhere
• For business inquiries: emailhello@jan.ai
• For jobs: please emailhr@jan.ai

Beware of scams!

• We will never request your personal information.
• Our product is completely free; no paid version exists.
• We do not have a token or ICO.
• We are abootstrapped company, and don't have any external investors (yet). We're open to exploring opportunities with strategic partners want to tackleour mission together.

Jan is free and open source, under theAGPLv3 license.