openagent @ tabby ~ $

cat README.md

Tabby

Self-hosted AI coding assistant with code completion, chat, and agent capabilities that runs entirely on your infrastructure.

# 32K Stars · 1.6K Forks · Apache-2.0 License // verified 2026-06-04
tabby/main
$docker run -it --gpus all -p 8080:8080 tabbyml/tabby serve --model StarCoder-15B
Installing Tabby...
Tabby ready
$tabby --help
Reading tabby configuration & environment...
# core strengths

What makes Tabby different

Fully self-hosted

Runs entirely on your infrastructure with no external API calls or data leaving your network.

For regulated industries (healthcare, finance, government), Tabby is one of the few viable AI coding assistants because no code ever leaves the organization.

Multi-editor support

Works with VS Code, JetBrains, Vim, Emacs, and other editors through standardized plugins.

Teams with diverse editor preferences can standardize on one self-hosted AI backend.

Code completion + chat + agent

Provides inline code completion, conversational chat, and agentic task execution from a single self-hosted service.

One deployment covers the full spectrum of AI-assisted development without relying on external services.

Open model support

Works with any open-source model including Llama, DeepSeek, Qwen, and fine-tuned custom models.

Teams can choose, fine-tune, or build custom models for their specific codebase and domain.
# quick start

Your first command

terminal
$docker run -it --gpus all -p 8080:8080 tabbyml/tabby serve --model StarCoder-15B
# use cases

How developers use Tabby

01

Air-gapped development

Deploy Tabby in an air-gapped environment with no internet access, running entirely on local GPU infrastructure.

02

Enterprise compliance

Meet SOC 2, HIPAA, or GDPR requirements by keeping all code and AI processing within your controlled infrastructure.

03

Custom model fine-tuning

Fine-tune open models on your codebase for better completion quality, then serve them through Tabby.

# comparison

How Tabby compares

Choose Tabby for self-hosted data sovereignty vs GitHub Copilot

Tabby runs entirely on your infrastructure with no data leaving your network. Copilot sends code snippets to GitHub's servers for processing.

# faq

Questions

Q: What should I check before using Tabby?

Start with one safe workflow for Tabby. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.

Q: Is Tabby open source?

Tabby is listed with Apache-2.0 based on the official source links in this profile. Re-check the repository, model card, or docs before production use.

Q: What hardware does Tabby need?

Tabby requires a machine with a GPU for good performance. It supports NVIDIA GPUs and Apple Silicon, and can run CPU-only with reduced speed.