A self-contained, open-source AI coding assistant designed as an on-premises alternative to GitHub Copilot. It operates without requiring a DBMS or cloud service and supports consumer-grade GPUs for local inference.
Project overview
A self-contained, open-source AI coding assistant designed as an on-premises alternative to GitHub Copilot. It operates without requiring a DBMS or cloud service and supports consumer-grade GPUs for local inference.
Project type
AI Coding
Use cases
Knowledge Q&A · Coding & Development
Deployment
Docker / Docker Compose
License
License pending
Best for
Development teams seeking a self-hosted coding assistant that runs locally without cloud dependencies or database requirements.
Key capabilities
Exposes an OpenAPI interface to integrate with existing infrastructure like Cloud IDEs.
Utilizes repository-level context to provide relevant code suggestions.
Limitations and risks
Requires loading and configuring specific language models, such as StarCoder or Qwen2, for operation.
Using GPU acceleration requires appropriate hardware, such as consumer GPUs with CUDA.
Getting started
Setup is rated as easy due to an available 1-minute Docker quickstart.
Evidence and sources
README: 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 f…
README: * **08/31/2023** Tabby's first stable release [v0.0.1](https://github.com/TabbyML/tabby/releases/tag/v0.0.1) 🥳.
README: * **07/05/2024** Tabby [v0.13.0](https://github.com/TabbyML/tabby/releases/tag/v0.13.0) introduces ***Answer Engine***, a central knowledge engine for internal engineering teams.…
README: * **10/15/2023** RAG-based code completion is enabled by detail in [v0.3.0](https://github.com/TabbyML/tabby/releases/tag/v0.3.0)🎉! Check out the [blogpost](https://tabby.tabbyml.…
README: * **03/20/2024** [v0.9](https://github.com/TabbyML/tabby/releases/tag/v0.9.1) released, highlighting a full feature admin UI.