AI · Early access

Tabby hosting on your own server

A self-hosted AI coding assistant, similar to GitHub Copilot.

Early access. Join the list and we email you when Tabby opens on VPS.

What Tabby does

Tabby is a self-hosted code completion and chat assistant that plugs into editors like VS Code and JetBrains IDEs, giving teams Copilot-style suggestions without sending source code to a third-party API. It can run its own models or connect to external LLM providers. It supports popular open code models, so a team can pick a model sized to their available GPU hardware.

Tabby at a glance

License: Apache-2.0 (core), proprietary Enterprise features
Source code: github.com/TabbyML/tabby
Website: tabby.tabbyml.com
Runs on: Your own server (VPS)
Good to know: Needs a GPU for good speed with local code models; can also proxy to an external LLM API instead.

Private code completion for teams
Keeping proprietary code off third-party APIs
In-editor AI coding chat

Tabby, connected to the rest of your business

On your domain
Tabby answers at an address like tabby.yourbusiness.com, with SSL and daily backups switched on.
Mail from your address
Tabby sends its emails from your CloudWish business mailbox. Business email
AI with a cap you set
Give Tabby its own AI key with a monthly spend cap. Usage shows as its own line on your bill. AI in your apps (early access)