10 Sentinels Active
SENTINEL 01: [AEGIS] AUDITING POCKETBASE INFRASTRUCTURE...
Back to Self-Hosted Stacks
TabbyML

Deploy TabbyML

Self-hosted AI coding assistant. An open-source, self-hosted alternative to GitHub Copilot.

Quick Start

1

Create a directory

mkdir tabby-self-hosted && cd tabby-self-hosted
2

Create config file

Copy the content from the Config tab below into a file named docker-compose.yml

3

Deploy

docker compose up -d
Fast Track

Deploy TabbyML in Minutes

Use our optimized Docker templates to deploy TabbyML on any cloud provider. Get $200 in free credit to start on DigitalOcean.

Start with free creditDeploy on DigitalOcean
$200

Metadata

License
Apache License 2.0
Language
Rust
Last Updated
6/30/2026
Category
AI Coding

Configuration

yaml

# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
# 🚀 BUILT & MAINTAINED BY THE ALTSTACK
# 🌍 https://thealtstack.com
# 💡 Open-source deployment templates for modern self-hosting.
# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

# Docker Compose for Tabby (AI Coding Assistant)
version: '3.8'

services:
  tabby:
    image: tabbyml/tabby
    container_name: tabby
    command: serve --model TabbyML/StarCoder-1B --device cpu
    ports:
      - "8080:8080"
    volumes:
      - tabby_data:/data
    networks:
      - tabby_net
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 3

networks:
  tabby_net:
    driver: bridge

volumes:
  tabby_data:

Community Notes

Help others by adding context, corrections, or warnings about this tool. Sign in to contribute.

No community notes yet. Be the first to add context.