# πΎ Tabby
[π Docs](https://tabby.tabbyml.com/docs/welcome/) β’ [π¬ Slack](https://links.tabbyml.com/join-slack) β’ [πΊοΈ Roadmap](https://tabby.tabbyml.com/docs/roadmap/)
[![latest release](https://shields.io/github/v/release/TabbyML/tabby)](https://github.com/TabbyML/tabby/releases/latest)
[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](https://makeapullrequest.com)
[![Docker pulls](https://img.shields.io/docker/pulls/tabbyml/tabby)](https://hub.docker.com/r/tabbyml/tabby)
[![codecov](https://codecov.io/gh/TabbyML/tabby/graph/badge.svg?token=WYVVH8MKK3)](https://codecov.io/gh/TabbyML/tabby)
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.
## π₯ What's New
* **10/30/2024** Tabby [v0.19.0](https://github.com/TabbyML/tabby/releases/tag/v0.19.0) featuring recent shared threads on the main page to improve their discoverability.
* **07/09/2024** πAnnounce [Codestral integration in Tabby](https://tabby.tabbyml.com/blog/2024/07/09/tabby-codestral/)!
* **07/05/2024** Tabby [v0.13.0](https://github.com/TabbyML/tabby/releases/tag/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](https://marketplace.visualstudio.com/items/TabbyML.vscode-tabby/changelog) 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 πblogpost drop on [an enhanced code context understanding](https://tabby.tabbyml.com/blog/2024/06/11/rank-fusion-in-tabby-code-completion/) in Tabby!
* **06/06/2024** Tabby [v0.12.0](https://github.com/TabbyML/tabby/releases/tag/v0.12.0) release brings π**seamless integrations** (Gitlab SSO, Self-hosted GitHub/GitLab, etc.), to βοΈ**flexible configurations** (HTTP API integration) and π**expanded capabilities** (repo-context in Code Browser)!
Archived
* **05/22/2024** Tabby [VSCode 1.6](https://marketplace.visualstudio.com/items?itemName=TabbyML.vscode-tabby) comes with **multiple choices** in inline completion, and the **auto-generated commit messages**π±π»!
* **05/11/2024** [v0.11.0](https://github.com/TabbyML/tabby/releases/tag/v0.11.0) brings significant enterprise upgrades, including π**storage usage** stats, π**GitHub & GitLab** integration, π**Activities** page, and the long-awaited π€**Ask Tabby** feature!
* **04/22/2024** [v0.10.0](https://github.com/TabbyML/tabby/releases/tag/v0.10.0) released, featuring the latest **Reports** tab with team-wise analytics for Tabby usage.
* **04/19/2024** π£ Tabby now incorporates [locally relevant snippets](https://github.com/TabbyML/tabby/pull/1844)(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](https://tabby.tabbyml.com/docs/models/)!
* **03/20/2024** [v0.9](https://github.com/TabbyML/tabby/releases/tag/v0.9.1) released, highlighting a full feature admin UI.
* **12/23/2023** Seamlessly [deploy Tabby on any cloud](https://tabby.tabbyml.com/docs/installation/skypilot/) with [SkyServe](https://skypilot.readthedocs.io/en/latest/serving/sky-serve.html) π« from SkyPilot.
* **12/15/2023** [v0.7.0](https://github.com/TabbyML/tabby/releases/tag/v0.7.0) released with team management and secured access!
* **10/15/2023** RAG-based code completion is enabled by detail in [v0.3.0](https://github.com/TabbyML/tabby/releases/tag/v0.3.0)π! Check out the [blogpost](https://tabby.tabbyml.com/blog/2023/10/16/repository-context-for-code-completion/) explaining how Tabby utilizes repo-level context to get even smarter!
* **11/27/2023** [v0.6.0](https://github.com/TabbyML/tabby/releases/tag/v0.6.0) released!
* **11/09/2023** [v0.5.5](https://github.com/TabbyML/tabby/releases/tag/v0.5.5) released! With a redesign of UI + performance improvement.
* **10/24/2023** β³οΈ Major updates for Tabby IDE plugins across [VSCode/Vim/IntelliJ](https://tabby.tabbyml.com/docs/extensions)!
* **10/04/2023** Check out the [model directory](https://tabby.tabbyml.com/docs/models/) for the latest models supported by Tabby.
* **09/18/2023** Apple's M1/M2 Metal inference support has landed in [v0.1.1](https://github.com/TabbyML/tabby/releases/tag/v0.1.1)!
* **08/31/2023** Tabby's first stable release [v0.0.1](https://github.com/TabbyML/tabby/releases/tag/v0.0.1) π₯³.
* **08/28/2023** Experimental support for the [CodeLlama 7B](https://github.com/TabbyML/tabby/issues/370).
* **08/24/2023** Tabby is now on [JetBrains Marketplace](https://plugins.jetbrains.com/plugin/22379-tabby)!
## π Getting Started
You can find our documentation [here](https://tabby.tabbyml.com/docs/getting-started).
- π [Installation](https://tabby.tabbyml.com/docs/installation/)
- π» [IDE/Editor Extensions](https://tabby.tabbyml.com/docs/extensions/)
- βοΈ [Configuration](https://tabby.tabbyml.com/docs/configuration)
### Run Tabby in 1 Minute
The easiest way to start a Tabby server is by using the following Docker command:
```bash
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](https://tabbyml.github.io/tabby).
## π€ Contributing
Full guide at [CONTRIBUTING.md](https://github.com/TabbyML/tabby/blob/main/CONTRIBUTING.md);
### Get the Code
```bash
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](https://www.rust-lang.org/learn/get-started).
2. Install the required dependencies:
```bash
# For MacOS
brew install protobuf
# For Ubuntu / Debian
apt install protobuf-compiler libopenblas-dev
```
3. Install useful tools:
```bash
# For Ubuntu
apt install make sqlite3 graphviz
```
4. Now, you can build Tabby by running the command `cargo build`.
### Start Hacking!
... and don't forget to submit a [Pull Request](https://github.com/TabbyML/tabby/compare)
## π Community
- π€ [Twitter / X](https://twitter.com/Tabby_ML) - engage with TabbyML for all things possible
- π [LinkedIn](https://www.linkedin.com/company/tabbyml/) - follow for the latest from the community
- π [Newsletter](https://newsletter.tabbyml.com/archive) - subscribe to unlock Tabby insights and secrets
### π Activity
![Git Repository Activity](https://repobeats.axiom.co/api/embed/e4ef0fbd12e586ef9ea7d72d1fb4f5c5b88d78d5.svg "Repobeats analytics image")
### π Star History
[![Star History Chart](https://api.star-history.com/svg?repos=tabbyml/tabby&type=Date)](https://star-history.com/#tabbyml/tabby&Date)