Deploy Continue.dev on Your RamNode VPS

Transform your coding workflow with AI-powered code completion, chat, and editing capabilities running on your own infrastructure.

45-60 min

Setup Time

4GB RAM

Recommended

Intermediate

Difficulty

Port 3000

Default Port

Why Choose Continue.dev on Your Own VPS?

Continue.dev is an open-source AI code assistant that brings powerful code completion, chat, and editing capabilities directly into your development environment. Unlike cloud-based solutions, Continue.dev gives you complete control over your AI coding assistant by running it on your own infrastructure.

Privacy and Security

Your code never leaves your infrastructure. Perfect for proprietary codebases and organizations with strict data governance requirements.

Full Customization

Complete control over model selection and configuration. Choose from various AI models including local Ollama models.

Cost Control

Predictable hosting costs without per-token pricing. Pay only for your VPS, not for every API call.

Consistent Performance

Dedicated resources ensure reliable response times without rate limits or throttling.

Prerequisites

Recommended VPS Plan

We recommend the 4GB Standard Cloud VPS plan for optimal Continue.dev performance with local AI models:

4GB RAM minimum (8GB+ for better performance)
2+ CPU cores for model processing
80GB+ SSD storage for AI models
Sufficient bandwidth for development workflow

View Cloud VPS Plans

Server Requirements

Ubuntu 22.04 LTS or newer
4GB+ RAM (8GB recommended)
20GB+ available storage
2+ CPU cores

Local Requirements

VS Code or compatible editor
SSH client for server access
Basic command-line familiarity
Domain name (optional)

Step 1: Initial Server Setup

Update System and Install Essentials

# Update the system

sudo apt update && sudo apt upgrade -y

# Install essential packages

sudo apt install -y curl wget git unzip software-properties-common apt-transport-https ca-certificates gnupg lsb-release

Configure Firewall

sudo apt install ufw -y

sudo ufw default deny incoming

sudo ufw default allow outgoing

sudo ufw allow 22

sudo ufw allow 80

sudo ufw allow 443

sudo ufw allow 3000

sudo ufw enable

Step 2: Install Docker and Docker Compose

Install Docker

Docker simplifies dependency management and ensures consistent deployment

# Add Docker's official GPG key

curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg

# Add Docker repository

echo "deb [arch=amd64 signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

# Update and install Docker

sudo apt update

sudo apt install -y docker-ce docker-ce-cli containerd.io

# Add user to docker group

sudo usermod -aG docker $USER

# Start and enable Docker

sudo systemctl start docker

sudo systemctl enable docker

Install Docker Compose

sudo curl -L "https://github.com/docker/compose/releases/latest/download/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose

sudo chmod +x /usr/local/bin/docker-compose

docker-compose --version

# Log out and back in for group changes

newgrp docker

Step 3: Download and Configure Continue.dev

Clone Repository

cd /opt

sudo git clone https://github.com/continuedev/continue.git

sudo chown -R $USER:$USER continue

cd continue

Create Environment Configuration

cp .env.example .env

nano .env

Configure these key variables:

# Server configuration

PORT=3000

HOST=0.0.0.0

# Security

CONTINUE_SECRET_KEY=your_secure_random_key_here

# Model configuration

DEFAULT_MODEL=codellama:7b

# Database

DATABASE_URL=sqlite:///app/data/continue.db

# Privacy

TELEMETRY_ENABLED=false

Generate Secure Key

Generate a secure secret key:

openssl rand -hex 32

Use the output as your CONTINUE_SECRET_KEY

Step 4: Set Up Ollama for Local AI Models

Install Ollama

Ollama provides local AI models for Continue.dev

curl -fsSL https://ollama.ai/install.sh | sh

# Start Ollama service

sudo systemctl start ollama

sudo systemctl enable ollama

Configure Ollama for Docker

# Create service override directory

sudo mkdir -p /etc/systemd/system/ollama.service.d

# Create override configuration

sudo tee /etc/systemd/system/ollama.service.d/override.conf > /dev/null <<EOF

[Service]

Environment="OLLAMA_HOST=0.0.0.0:11434"

EOF

# Reload and restart

sudo systemctl daemon-reload

sudo systemctl restart ollama

Download AI Models

# Download CodeLlama (optimized for code)

ollama pull codellama:7b

# Optional: Download other models

ollama pull llama2:7b

ollama pull mistral:7b

# List installed models

ollama list

Step 5: Create Docker Compose and Deploy

Create Docker Compose Configuration

nano docker-compose.yml

Add this configuration:

version: '3.8'

services:

continue-server:

build:

context: .

dockerfile: Dockerfile

ports:

- "3000:3000"

environment:

- PORT=3000

- HOST=0.0.0.0

- CONTINUE_SECRET_KEY=${CONTINUE_SECRET_KEY}

- DEFAULT_MODEL=codellama:7b

- OLLAMA_BASE_URL=http://host.docker.internal:11434

volumes:

- ./data:/app/data

- ./config:/app/config

restart: unless-stopped

extra_hosts:

- "host.docker.internal:host-gateway"

# Create required directories

mkdir -p data config ollama-data

chmod 755 data config ollama-data

Build and Start Services

docker-compose build

docker-compose up -d

# Check status

docker-compose ps

# View logs

docker-compose logs -f continue-server

Verify installation:

curl http://localhost:3000/health

curl http://localhost:11434/api/tags

Step 6: Configure SSL/TLS with Nginx

Install and Configure Nginx

Recommended for production deployments

sudo apt install nginx -y

sudo nano /etc/nginx/sites-available/continue

Add this configuration:

server {

listen 80;

server_name your-domain.com;

location / {

proxy_pass http://127.0.0.1:3000;

proxy_http_version 1.1;

proxy_set_header Upgrade $http_upgrade;

proxy_set_header Connection 'upgrade';

proxy_set_header Host $host;

proxy_set_header X-Real-IP $remote_addr;

proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;

proxy_read_timeout 86400;

}

# Enable site

sudo ln -s /etc/nginx/sites-available/continue /etc/nginx/sites-enabled/

sudo rm /etc/nginx/sites-enabled/default

sudo nginx -t

sudo systemctl restart nginx

Install SSL Certificate

sudo apt install certbot python3-certbot-nginx -y

sudo certbot --nginx -d your-domain.com

sudo certbot renew --dry-run

# Update firewall

sudo ufw allow 'Nginx Full'

sudo ufw delete allow 3000

Step 7: Configure Continue.dev Client

Install VS Code Extension

Open Visual Studio Code
Go to Extensions (Ctrl+Shift+X)
Search for "Continue"
Install the Continue extension by Continue

Configure Extension

Open VS Code settings (Ctrl+,) and search for "Continue", then set your server URL. Alternatively, create a .continuerc.json file in your project root with your server configuration.

Step 8: Performance Optimization

Optimize Docker Resources

echo "DOCKER_DEFAULT_PLATFORM=linux/amd64" >> .env

Configure Model Performance

# Use optimized models

ollama pull codellama:7b-code

# Lower memory usage

echo 'OLLAMA_NUM_PARALLEL=1' | sudo tee -a /etc/systemd/system/ollama.service.d/override.conf

Monitor Resources

docker stats

htop

df -h

Step 9: Backup and Maintenance

Regular Updates

cd /opt/continue

git pull origin main

docker-compose build --no-cache

docker-compose up -d

# Update models

ollama pull codellama:7b

# Clean up

docker system prune -f

Automated Backups

Create a backup script to regularly backup your Continue.dev data and configuration files. Store backups in a secure location and test restoration procedures regularly.

Troubleshooting

Service Won't Start

docker-compose logs continue-server

docker-compose logs ollama

sudo journalctl -u ollama -f

Memory Issues

free -h

# Use smaller quantized models

ollama pull codellama:7b-instruct-q4_0

Connection Issues

curl -v http://localhost:3000/health

curl -v http://your-vps-ip:3000/health

sudo ufw status

docker network ls

Frequently Asked Questions

Ready to Deploy?

Get started with RamNode's high-performance VPS hosting

View VPS Plans More Deployment Guides