🐾 Tabby

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.

🔥 What's New

11/27/2023 v0.6.0 released!
10/24/2023 ⛳️ Major updates for Tabby IDE plugins across VSCode/Vim/IntelliJ!
10/15/2023 RAG-based code completion is enabled by detail in v0.3.0🎉! Check out the blogpost explaining how Tabby utilizes repo-level context to get even smarter!

Archived

11/09/2023 v0.5.5 released! With a redesign of UI + performance improvement.
10/04/2023 Check out the model directory for the latest models supported by Tabby.
09/18/2023 Apple's M1/M2 Metal inference support has landed in v0.1.1!
08/31/2023 Tabby's first stable release v0.0.1 🥳.
08/28/2023 Experimental support for the CodeLlama 7B.
08/24/2023 Tabby is now on JetBrains Marketplace!

You can find our documentation here.

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.

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.

# For MacOS
brew install protobuf

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

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