Tabby is an open-source, self-hosted AI coding assistant positioned as an on-premises alternative to cloud services such as GitHub Copilot. It provides code completion, chat, repository-aware context, and developer-assistance features while allowing organizations to run the backend on their own infrastructure.

The project is self-contained and does not require an external database or mandatory cloud service. It exposes an OpenAPI interface, supports consumer-grade GPUs, and integrates with development environments through editor plugins. Over time, Tabby has added repository indexing, RAG-based code completion, team management, authentication, documentation context, GitLab merge-request context, persistent answer pages, and richer chat workflows.

Tabby is suited to developers and organizations that want AI-assisted coding while keeping source code and inference infrastructure under their own control. It can be particularly attractive in privacy-sensitive or regulated environments, and its open architecture makes it possible to integrate the coding assistant with internal development platforms rather than relying exclusively on a proprietary hosted service.