tabby

App Featured

Self-hosted AI coding assistant

Checked ยท Sources

Downloads
8,774
Dependents
Not applicable
Stars
33,925
Forks
1,795
Contributors
116
Commits
3,695
Latest release

About

From the project README ยท

๐Ÿ“š Docs โ€ข ๐Ÿ’ฌ Slack โ€ข ๐Ÿ—บ๏ธ Roadmap

English | ็ฎ€ไฝ“ไธญๆ–‡ | ๆ—ฅๆœฌ่ชž

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features:

  • Self-contained, with no need for a DBMS or cloud service.
  • OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE).
  • Supports consumer-grade GPUs.

Demo

๐Ÿ”ฅ What's New

  • 12/12/2025 Get your GitHub issues implemented by connecting them to Pochi tasks and create PRs directly from the sidebar with a breakdown of CI/Lint/Test results vscode@0.20.0.
  • 07/02/2025 v0.30 supports indexing GitLab Merge Request as Context!
  • 05/25/2025 ๐Ÿ’กInterested in joining Agent private preview? DM in X for early waitlist approval!๐ŸŽซ
  • 05/20/2025 Enhance Tabby with your own documentation๐Ÿ“ƒ through REST APIs in v0.29! ๐ŸŽ‰
  • 05/01/2025 v0.28 transforming Answer Engine messages into persistent, shareable Pages
  • 03/31/2025 v0.27 released with a richer @ menu in the chat side panel.

Archived

Read the full README
  • 02/05/2025 LDAP Authentication and better notification for background jobs coming in Tabby v0.24.0!โœจ
  • 02/04/2025 VSCode 1.20.0 upgrade! @-mention files to add them as chat context, and edit inline with a new right-click option are available!
  • 01/10/2025 Tabby v0.23.0 featuring enhanced code browser experience and chat side panel improvements!
  • 12/24/2024 Introduce Notification Box in Tabby v0.22.0!
  • 12/06/2024 Llamafile deployment integration and enhanced Answer Engine user experience are coming in Tabby v0.21.0!๐Ÿš€
  • 11/10/2024 Switching between different backend chat models is supported in Answer Engine with Tabby v0.20.0!
  • 10/30/2024 Tabby v0.19.0 featuring recent shared threads on the main page to improve their discoverability.
  • 07/09/2024 ๐ŸŽ‰Announce Codestral integration in Tabby!
  • 07/05/2024 Tabby v0.13.0 introduces Answer Engine, a central knowledge engine for internal engineering teams. It seamlessly integrates with dev team's internal data, delivering reliable and precise answers to empower developers.
  • 06/13/2024 VSCode 1.7 marks a significant milestone with a versatile Chat experience throughout your coding experience. Come and they the latest chat in side-panel and editing via chat command!
  • 06/10/2024 Latest ๐Ÿ“ƒblogpost drop on an enhanced code context understanding in Tabby!
  • 06/06/2024 Tabby v0.12.0 release brings ๐Ÿ”—seamless integrations (Gitlab SSO, Self-hosted GitHub/GitLab, etc.), to โš™๏ธflexible configurations (HTTP API integration) and ๐ŸŒexpanded capabilities (repo-context in Code Browser)!
  • 05/22/2024 Tabby VSCode 1.6 comes with multiple choices in inline completion, and the auto-generated commit messages๐Ÿฑ๐Ÿ’ป!
  • 05/11/2024 v0.11.0 brings significant enterprise upgrades, including ๐Ÿ“Šstorage usage stats, ๐Ÿ”—GitHub & GitLab integration, ๐Ÿ“‹Activities page, and the long-awaited ๐Ÿค–Ask Tabby feature!
  • 04/22/2024 v0.10.0 released, featuring the latest Reports tab with team-wise analytics for Tabby usage.
  • 04/19/2024 ๐Ÿ“ฃ Tabby now incorporates locally relevant snippets(declarations from local LSP, and recently modified code) for code completion!
  • 04/17/2024 CodeGemma and CodeQwen model series have now been added to the official registry!
  • 03/20/2024 v0.9 released, highlighting a full feature admin UI.
  • 12/23/2023 Seamlessly deploy Tabby on any cloud with SkyServe ๐Ÿ›ซ from SkyPilot.
  • 12/15/2023 v0.7.0 released with team management and secured access!
  • 10/15/2023 RAG-based code completion is enabled by detail in v0.3.0๐ŸŽ‰! Check out the blogpost explaining how Tabby utilizes repo-level context to get even smarter!
  • 11/27/2023 v0.6.0 released!
  • 11/09/2023 v0.5.5 released! With a redesign of UI + performance improvement.
  • 10/24/2023 โ›ณ๏ธ Major updates for Tabby IDE plugins across VSCode/Vim/IntelliJ!
  • 10/04/2023 Check out the model directory for the latest models supported by Tabby.
  • 09/18/2023 Apple's M1/M2 Metal inference support has landed in v0.1.1!
  • 08/31/2023 Tabby's first stable release v0.0.1 ๐Ÿฅณ.
  • 08/28/2023 Experimental support for the CodeLlama 7B.
  • 08/24/2023 Tabby is now on JetBrains Marketplace!

๐Ÿ‘‹ Getting Started

You can find our documentation here.

Run Tabby in 1 Minute

The easiest way to start a Tabby server is by using the following Docker command:

docker run -it \
  --gpus all -p 8080:8080 -v $HOME/.tabby:/data \
  tabbyml/tabby \
  serve --model StarCoder-1B --device cuda --chat-model Qwen2-1.5B-Instruct

For additional options (e.g inference type, parallelism), please refer to the documentation page.

๐Ÿค Contributing

Full guide at CONTRIBUTING.md;

Get the Code
git clone --recurse-submodules https://github.com/TabbyML/tabby
cd tabby

If you have already cloned the repository, you could run the git submodule update --recursive --init command to fetch all submodules.

Build
  1. Set up the Rust environment by following this tutorial.

  2. Install the required dependencies:

# For MacOS
brew install protobuf

# For Ubuntu / Debian
apt install protobuf-compiler libopenblas-dev
  1. Install useful tools:
# For Ubuntu
apt install make sqlite3 graphviz
  1. Now, you can build Tabby by running the command cargo build.
Start Hacking!

... and don't forget to submit a Pull Request

๐ŸŒ Community

  • ๐ŸŽค Twitter / X - engage with TabbyML for all things possible
  • ๐Ÿ“š LinkedIn - follow for the latest from the community
  • ๐Ÿ’Œ Newsletter - subscribe to unlock Tabby insights and secrets
๐Ÿ”† Activity
๐ŸŒŸ Star History
License
Not measured
Crate facts
Not measured
  • Runs on, Native code and Python bindings read crates on crates.io. This entry lists no crate.

Compare with similar projects

Order: strongest tier first, then most downloads, then name, with unmeasured values last. A library counts downloads over 30 days. An app counts binary downloads per release. An app with none counts its crate downloads over 30 days. ML Rust runs this catalogue, so its closest project always gets a row.

tabby beside the projects that share a topic with it
ProjectDownloadsDependentsStarsLatest releaseRuns on (GPU)Native codeLicense
tabby This page App Featured

Self-hosted AI coding assistant

8,774 binary downloads per release Not applicable 33,925 Not measured Not measured Not measured
llmfit App Featured

Right-size LLM models to your system hardware. Interactive TUI and CLI to match models against available RAM, CPU, and GPU.

3,821 binary downloads per release Not applicable 38,787 1.1.20 Metal No native code found MIT
agent App Listed

Ship your code, on autopilot. An open source agent that lives on your machines 24/7 and keeps your apps running. ๐Ÿฆ€

19,860 binary downloads per release Not applicable 1,859 0.3.88 GPU support unknown Binds native code: tree-sitter, tree-sitter-language, tikv-jemalloc-sys (feature jemalloc) Apache-2.0
code2prompt App Listed

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

2,317 binary downloads per release Not applicable 7,756 4.3.0 GPU support unknown Binds native code: libgit2-sys, libz-sys MIT
lsp-ai App Listed Dormant

LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.

2,314 binary downloads per release Not applicable 3,210 0.7.0 CUDA, Metal Binds native code: tree-sitter, tree-sitter-language, llama-cpp-sys-2 (feature cuda). Build uses a native toolchain: cc MIT

OpenTelemetry components and utilities for Langfuse LLM observability

2,119 downloads over 30 days 2 4 0.7.2 GPU support unknown No native code found Apache-2.0 OR MIT
axp App Listed

An open protocol that gives AI agents a secure, sandboxed place to run code and use tools โ€” with lean context usage. AXP works alongside MCP

Not measured Not applicable 3 Not measured Not measured Not measured Apache-2.0
Why FeaturedIt passes every Featured gate.

What it meets

  • Its use signals read: binary downloads 26324, Homebrew unknown, Repology families unknown, Docker growth unknown. Featured needs 2 of these to reach their limits.
  • It also passes the repository route, which counts as one use signal: 33,925 stars, 1,795 forks and 116 contributors. It needs 4,539 stars, 434 forks and 79 contributors together.
  • The last activity is on 30 Jun 2026, 132 days ago. The rules expect an update within 365 days. Dormancy rule

Not measured: First release.

Exact rules: Featured app. The check on applied thresholds version 9.

Every rule outcome, as the check records it
  • expected-interval: app: E = 365 days
  • dormancy: last activity 2026-06-30, 132 days ago, E = 365: active
  • featured: featured: binary downloads 26324, Homebrew unknown, Repology families unknown, Docker growth unknown, repository route stars 33925 (needs 4539), forks 1795 (needs 434), contributors 116 (needs 79)

Measurements and sources

Each signal row shows the raw value, its source and the fetch date. The Sources list gathers every distinct source on this page. Movement needs more history.

Sources4 sources
Adoption8,774 binary downloads per release4 not measured
Adoption measurements
SignalValueSourceFetchedCounts
Active dependentsNot measuredYes
New dependents (365 days)Not measuredYes
Peak active dependentsNot measuredYes
Active dependents as a share of the peakNot measuredYes
Binary downloads per release8774GitHub releasesYes
MaintenanceLatest human commit: 4 months ago7 not measured
Maintenance measurements
SignalValueSourceFetchedCounts
Latest human commit2026-06-30GitHub repositoryYes
Latest release2026-02-09GitHub releasesYes
First releaseNot measuredYes
Latest versionNot measuredYes
Days the oldest outside issue waits for a reply341GitHub repositoryYes
Maintainer replies over 365 days9GitHub repositoryYes
Repository archivedfalseGitHub repositoryYes
Repository gonefalseGitHub repositoryYes
Release commit or manifest in the repoNot measuredYes
Published docsNot measuredYes
Latest release fails cargo checkNot measuredYes
Build check dateNot measuredYes
Build check toolchainNot measuredYes
SecurityNot measured
Security measurements
SignalValueSourceFetchedCounts
Unpatched vulnerabilities past the grace windowNot measuredYes
RustSec unmaintained advisoryNot measuredYes
Deprecation noticeNot measuredYes
Deprecated requirementNot measuredYes
Distribution26,324 binary downloads over the last 3 releases10 not measured
Distribution measurements
SignalValueSourceFetchedCounts
ReleasesNot measuredYes
Downloads over 30 daysNot measuredYes
Binary downloads over the last 3 releases26324GitHub releasesYes
Homebrew installs on request over 365 daysNot measuredYes
Repology repository familiesNot measuredYes
Docker pull growth over 90 daysNot measuredYes
Docker pulls at the growth baselineNot measuredYes
Every version a prereleaseNot measuredYes
Every version 0.0.xNot measuredYes
Every version yankedNot measuredYes
Crate deleted from crates.ioNot measuredYes
Repository33,925 stars, 1,795 forks, 116 contributors, 3,695 commits. Stars alone never qualify a project.1 not measured
Repository measurements
SignalValueSourceFetchedCounts
GitHub stars33925GitHub repositoryYes โ€” one part of the repository route
GitHub forks1795GitHub repositoryYes โ€” one part of the repository route
Contributors with a GitHub account116GitHub contributorsYes โ€” one part of the repository route
Commits on the default branch3695GitHub repositoryNo
Repository's main crate left out of the entryNot measuredYes
Facts that never count
Facts that never count measurements
SignalValueSourceFetchedCounts
LicenseNot measuredNo
Runs on, from listed crates and their direct dependenciesNot measuredNo
What shows each backendNot measuredNo
Native code, from listed crates and their dependenciesNot measuredNo
Python bindings, from direct dependencies of listed cratesNot measuredNo
Crates that depend on a listed crate directlyNot measuredNo

Corrections and review history

Report a correction

No correction applies to this entry.

Judgments

A judgment enters only through an approved issue and a merged pull request.

No judgment applies to this entry.