Connect with us


Tabby – Self-hosted AI coding assistant

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

Warning Tabby is still in the alpha phase

Tabby Features

  • 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).

Get started


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 \

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/

Tabby on GitHub:
Platform: coding
⭐️: 3.6К