mirrors/tabby
1
0
Fork 0
mirror of https://github.com/TabbyML/tabby synced 2024-11-22 00:08:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,455 Commits 124 Branches 389 Tags 1,013 MiB
Rust 90.5%
Python 6.1%
HTML 1.7%
TypeScript 0.6%
Scheme 0.5%
Other 0.6%
fa866516c7
Go to file
boxbeam fa866516c7
fix(core): Change to clippy lint (#1425)
2024-02-09 11:28:39 -08:00
.github chore: add paths to test-rust.yml push event 2024-02-08 11:24:05 -08:00
ci feat: support build tabby on windows (#948) 2023-12-11 12:14:49 +08:00
clients chore(vim): Vim plugin hotfix 1.3.2. (#1351) 2024-02-01 15:31:00 +08:00
crates test: add lint to avoid unwrap (#1422) 2024-02-09 11:19:01 -08:00
ee refactor(scheduler): extract run_scheduler_now to handle scheduler error, instead of unwrapping (#1421) 2024-02-09 11:28:21 -08:00
experimental
python feat(loadtest): add loadtest tools (#906) 2023-11-28 14:34:00 +08:00
rules fix(core): Change to clippy lint (#1425) 2024-02-09 11:28:39 -08:00
website docs: add blog: Running Tabby as a Language Server (#1220) 2024-02-06 19:11:14 -08:00
.dockerignore feat: Add rocm builds and documentation (#1012) 2023-12-13 15:59:04 +08:00
.env refactor(db): Rewrite database code to use sqlx instead of rusqlite (#1340) 2024-02-01 09:38:37 -08:00
.gitattributes chore: exclude ee/tabby-webserver/ui to language stats 2023-11-17 15:50:27 -08:00
.gitignore
.gitmodules
.rustfmt.toml
Cargo.lock refactor(webserver): move id <-> HashId convertion traits to webserver (#1410) 2024-02-08 07:40:15 +00:00
Cargo.toml refactor: extract RepositoryAccess to abstract out scheduler reading (from config / database) (#1388) 2024-02-06 02:02:32 +00:00
CHANGELOG.md docs: update release info for 0.8.3 (#1400) 2024-02-06 12:53:00 -08:00
CODE_OF_CONDUCT.md docs: Create CODE_OF_CONDUCT.md (#1228) 2024-01-24 00:18:32 -08:00
codecov.yml chore: update codecov.yml 2024-02-08 13:15:46 -08:00
CONTRIBUTING.md docs: add CONTRIBUTING.md (#1185) 2024-01-11 08:39:08 -08:00
Dockerfile chore: add cpu build of tabby to docker image. (#1383) 2024-02-05 15:06:37 -08:00
LICENSE Update LICENSE 2024-01-10 23:16:11 -08:00
Makefile fix(core): Change to clippy lint (#1425) 2024-02-09 11:28:39 -08:00
MODEL_SPEC.md
package.json feat(lsp): add example VSCode client for Tabby agent LSP. (#1205) 2024-01-13 08:07:12 -08:00
README.md docs: add codecov to README.md 2024-02-08 00:04:04 -08:00
sgconfig.yml refactor(webserver): ensure only services could rely on tabby_db dire… (#1407) 2024-02-07 19:15:53 +00:00
yarn.lock fix(agent): tabby agent hotfix 1.3.3: disabled experimental features. (#1347) 2024-01-31 23:10:26 -08:00

README.md

🐾 Tabby

latest release PRs Welcome Docker pulls codecov

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.

Open in Playground

Demo

🔥 What's New

Archived
  • 10/15/2023 RAG-based code completion is enabled by detail in v0.3.0🎉! 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.
  • 10/04/2023 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 🥳.
  • 08/28/2023 Experimental support for the CodeLlama 7B.
  • 08/24/2023 Tabby is now on JetBrains Marketplace!

👋 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 TabbyML/StarCoder-1B --device cuda

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

🤝 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-get install protobuf-compiler libopenblas-dev
  1. Now, you can build Tabby by running the command cargo build.

Start Hacking!

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

🌍 Community

  • 🎤 Twitter / X - engage with TabbyML for all things possible
  • 📚 LinkedIn - follow for the latest from the community
  • 💌 Newsletter - subscribe to unlock Tabby insights and secrets

🌟 Star History

Star History Chart