Local AI

tabby

Self-hosted code completion that keeps the code inside your network

Visit official page 日本語で詳しく見る

Popularity

★ 34k

Last update

June 2026

License / pricing

Not stated

What it does

An on-premise alternative to GitHub Copilot: self-contained with no separate database or cloud dependency, happy on consumer GPUs, and exposed over an OpenAPI interface so it slots into existing IDE and cloud-IDE setups. Suggestion quality tracks the model and hardware you give it, so a small model on modest hardware feels correspondingly thin. Note the licence split — the core is Apache 2.0 but everything under ee/ carries a separate enterprise licence, worth checking against the features you actually need.

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

Screenshots & visuals

Before you start

Setup difficultySome setup needed
Command lineRequired
API keyRequired
Sends data onlineYes

Judged automatically from the project's own metadata. Always confirm on the official page.

tabby FAQ

Is tabby free?: tabby itself is free, but it needs an API key for an external AI service. That service charges separately, though some have a free tier.
Do I need to install anything or write code to use tabby?: It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.
Does tabby work on a phone?: No. It needs a computer.
Can I use tabby commercially?: The project does not state a clear licence, so commercial use cannot be confirmed here. Check the official page or ask the author before using it at work.

How it compares

The conditions that decide whether you can actually use it, side by side.

Tool	Command line	API key	Sends data out	Phone	Commercial use
tabby (this page)	Required	Required	Yes	No	With conditions
Ollama	Required	Not needed	No	No	Yes
Open WebUI	Required	Not needed	No	No	Yes
llama.cpp	Required	Not needed	No	No	Yes

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.

Other local ai tools

Ollama

Run AI models on your own computer with one command

Open WebUI

A ChatGPT-style interface for your local AI

llama.cpp

The lightweight engine that runs LLMs anywhere

vLLM

Serve AI models fast and at scale

Browse all tools Home

What it does

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

tabby FAQ

Is tabby free?

tabby itself is free, but it needs an API key for an external AI service. That service charges separately, though some have a free tier.

Do I need to install anything or write code to use tabby?

It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.

Does tabby work on a phone?

No. It needs a computer.

Can I use tabby commercially?

The project does not state a clear licence, so commercial use cannot be confirmed here. Check the official page or ask the author before using it at work.

How it compares

The conditions that decide whether you can actually use it, side by side.

Tool	Command line	API key	Sends data out	Phone	Commercial use
tabby (this page)	Required	Required	Yes	No	With conditions
Ollama	Required	Not needed	No	No	Yes
Open WebUI	Required	Not needed	No	No	Yes
llama.cpp	Required	Not needed	No	No	Yes

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.