OSS Tanbou
View on GitHubProject website

Tabby — self-hosted AI coding assistance for completion, chat, and repository context

OSS scale score 275.5OSS health 69Update pace 0 commits/30d
About these scores

OSS scale score is an unbounded metric that log-compresses and weights Stars, Watchers, Forks, and Contributors. Discovery score is the current OSS scale score minus the score at discovery. Update pace is commits in the last 30 days, growth momentum is the OSS scale score difference within the recent observation window, and OSS health is a 0–100 rating based on available recency, Community Health, and release data.

Stars
33,882
Primary language
Rust
License
Not determined
Repository last updated
Jun 30, 2026

Overview

Tabby is a self-hosted AI coding assistant providing code completion, chat, and repository-aware context. It is designed to run without a mandatory external DBMS or cloud service and supports consumer-grade GPUs.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Serve code completion, chat, and repository context from one self-hosted service

IDE extensions connect to the Tabby server for completion, chat, and context from repositories or documentation.

Sources: [2][3]

Deploy on owned GPUs or on-premises infrastructure

Tabby can be run with Docker and local inference so teams do not need a mandatory cloud AI service for the core assistant.

Sources: [2][3]

For teams that want AI coding assistance without sending source code to an external assistant

It fits environments with sensitive code or network constraints that still want Copilot-like completion and chat experiences.

Sources: [2]

Account for model operations and Community/Enterprise boundaries

Running models requires GPU/model capacity planning and maintenance. Most code is Apache-2.0, while ee/ is separately licensed.

Sources: [2][4]

Official sources

  1. [1]TabbyML/tabby repository(2026-09-20)
  2. [2]Tabby README(2026-09-20)
  3. [3]Tabby documentation(2026-09-20)
  4. [4]Tabby mixed license(2026-09-20)
Supplemental curator note

Tabby is relevant when code-assistance infrastructure should run on owned GPUs or on-premises systems rather than sending source code to a cloud assistant. Most code is Apache-2.0, while `ee/` uses a separate license, so verify edition boundaries for team and advanced features.

Try it in 3 steps

  1. 1

    Get the source

    git clone --depth 1 https://github.com/TabbyML/tabby.git
  2. 2

    Enter the repository

    cd tabby
  3. 3

    Check the official steps

    Continue with the commands in the README Installation, Quick Start, or Getting Started section.

    find . -maxdepth 1 -iname 'README*' -exec sed -n '1,220p' {} \; -quit
Check the official README

Growth

Growth trends · Last 30 days

33,882 Stars

Trend data is still being collected.

Development activity

Last 90 days · weekly

Commits (last 30 days)
0
Open PRs
76

Development activity is still being collected.

Built with

Categories and tags

Categories

Tags

GitHub data

GitHub dataView detailed GitHub data
View on GitHub

GitHub Topics

  • ai
  • codegen
  • coding-assistant
  • coding-language
  • developer-experience
  • developer-tools
  • gen-ai
  • llms
  • ide
Stars
33,882
Forks
1,788
Watchers
187
Open issues
262
Contributors
117
Primary language
Rust
License
Not determined
Repository last updated
Jun 30, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.