Self-hosted AI coding assistant. An opensource / on-prem alternative to GitHub Copilot.

Warning Tabby is still in the alpha phase

• Self-contained, with no need for a DBMS or cloud service
• Web UI for visualizing and configuration models and MLOps.
• OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE).
• Consumer level GPU supports (FP-16 weight loading with various optimization).

NOTE: Tabby requires Pascal or newer NVIDIA GPU.

Before running Tabby, ensure the installation of the NVIDIA Container Toolkit. We suggest using NVIDIA drivers that are compatible with CUDA version 11.8 or higher.

# Create data dir and grant owner to 1000 (Tabby run as uid 1000 in container)
mkdir -p data/hf_cache && chown -R 1000 data

docker run \
  --gpus all \
  -it --rm \
  -v "/$(pwd)/data:/data" \
  -v "/$(pwd)/data/hf_cache:/home/app/.cache/huggingface" \
  -p 5000:5000 \
  -e MODEL_NAME=TabbyML/J-350M \
  -e MODEL_BACKEND=triton \
  --name=tabby \
  tabbyml/tabby

You can then query the server using /v1/completions endpoint:

curl -X POST http://localhost:5000/v1/completions -H 'Content-Type: application/json' --data '{
    "prompt": "def binarySearch(arr, left, right, x):\n    mid = (left +"
}'

We also provides an interactive playground in admin panel localhost:5000/_admin

See deployment/skypilot/README.md

We offer multiple methods to connect to Tabby Server, including using OpenAPI and editor extensions.

Tabby has opened a FastAPI server at localhost:5000, which includes an OpenAPI documentation of the HTTP API. The same API documentation is also hosted at https://tabbyml.github.io/tabby

• VSCode Extension – Install from the marketplace, or open-vsx.org
• VIM Extension

Go to development directory.

make dev

or

make dev-triton # Turn on triton backend (for cuda env developers)