Yes, the open-source server software is 100% free to self-host.

Which IDEs are supported?

Plugins exist for VS Code, JetBrains IDEs, Vim, Neovim, and WebStorm.

What hardware is needed?

A modern GPU (e.g. NVIDIA RTX series or cloud GPU) is recommended.

Does source code leave the local network?

No, all code completion processing stays on your Tabby server.

Which models work best?

Popular models include Qwen 2.5 Coder, StarCoder, and Granite Code.

Tabby

Open-source self-hosted AI coding assistant server for local code completion.

Visit Website

What is Tabby?

TL;DR

Tabby is an open-source self-hosted AI coding assistant that provides private code completion, repository context, and IDE integrations without requiring source code to be sent to an external cloud service.

Self-hosted AI coding assistant server running on private GPU hardware
Real-time FIM inline code completion and repository context indexing
Plugins for VS Code, JetBrains IDEs, and Vim/Neovim editors

Explore with AI

About

Tabby is an open-source self-hosted AI coding assistant server designed for teams that want private code completion and repository-aware assistance on their own infrastructure. It provides AI-powered inline suggestions and coding help without requiring source code to be processed by a vendor-managed cloud service. Developers can connect Tabby to popular editors such as VS Code, JetBrains IDEs, Vim, and Neovim. Its server can use open-weight coding models and index repository context, giving engineers faster completion and code-aware assistance while keeping deployment under their control. Tabby is especially useful for security-conscious engineering organizations, backend teams, and companies that already operate private GPU or cloud infrastructure. The self-hosted approach can be valuable when source-code privacy, network control, or model customization matters more than a turnkey hosted coding assistant. For FutureStack, Tabby belongs in Coding because it is developer infrastructure rather than a generic chatbot. It is best for teams that want open-source AI coding assistance, private deployment, customizable models, and control over where code and inference workloads are processed.

Use Cases

Code Completion

Accelerate your coding with intelligent, AI-powered suggestions.

Answer Engine

Get instant answers to your coding questions within your IDE.

Inline Chat

Collaborate and code more efficiently with AI-driven inline chat.

Contextual Knowledge Retrieval

Faster DevelopmentBy leveraging TabbyML's Answer Engine, you can speed up your development workflow.

Key Features

Self-hosted AI coding assistant server running on private GPU hardware
Real-time FIM inline code completion and repository context indexing
Plugins for VS Code, JetBrains IDEs, and Vim/Neovim editors
Centralized admin dashboard for managing models, users, and usage metrics

Featured Tools

Wispr Flow

Voice-First Dictation

We may earn commissions from links to support our work. Learn more.