Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features:

• Self-contained, with no need for a DBMS or cloud service.
• OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE).
• Supports consumer-grade GPUs.

• 04/19/2024 📣 Tabby now incorporates locally relevant snippets(declarations from local LSP, and recently modified code) for code completion!
• 04/17/2024 CodeGemma and CodeQwen model series have now been added to the official registry!
• 03/20/2024 v0.9 released, highlighting a full feature admin UI.

You can find our documentation here.

• 📚 Installation
• 💻 IDE/Editor Extensions
• ⚙️ Configuration

The easiest way to start a Tabby server is by using the following Docker command:

docker run -it \
  --gpus all -p 8080:8080 -v $HOME/.tabby:/data \
  tabbyml/tabby \
  serve --model TabbyML/StarCoder-1B --device cuda

For additional options (e.g inference type, parallelism), please refer to the documentation page.

Full guide at CONTRIBUTING.md;

git clone --recurse-submodules https://github.com/TabbyML/tabby
cd tabby

If you have already cloned the repository, you could run the git submodule update --recursive --init command to fetch all submodules.

1. Set up the Rust environment by following this tutorial.

2. Install the required dependencies:

# For MacOS
brew install protobuf

# For Ubuntu / Debian
apt-get install protobuf-compiler libopenblas-dev

3. Now, you can build Tabby by running the command cargo build.

... and don't forget to submit a Pull Request

• 🎤 Twitter / X - engage with TabbyML for all things possible
• 📚 LinkedIn - follow for the latest from the community
• 💌 Newsletter - subscribe to unlock Tabby insights and secrets