Web AI Terminal

Key features

🖥️

Web SSH Terminal

Full browser-based terminal backed by Paramiko SSH. No client software needed.

🤖

Ollama AI Chat

Dedicated AI tab powered by local Ollama models. Use ? or /ai prefixes, or let errors auto-forward.

💬

Multi-tab Interface

Switch between terminal and chat panes in a unified, responsive UI.

⚡

Real-time Updates

Socket.IO keeps the terminal and AI responses live without page reloads.

🐳

Docker-ready

Single-command startup via Docker Hub or GitHub Container Registry. Compose file included.

🔒

Encrypted Credentials

SSH passwords are stored with Fernet symmetric encryption. Plain-text fallback disabled when a key is set.

Quick start

Pull and run in a single command — pick your preferred registry:

# Docker Hub
docker run -d --restart unless-stopped \
    -p 1010:1010 --name=webaiterminal \
    ftsiadimos/webaiterminal:latest

# GitHub Container Registry (identical image)
docker run -d --restart unless-stopped \
    -p 1010:1010 --name=webaiterminal \
    ghcr.io/ftsiadimos/webaiterminal:latest

Then open http://localhost:1010 in your browser.

git clone https://github.com/ftsiadimos/Web-Terminal-AI
cd Web-AI-Terminal
cp docker-compose.example.yml docker-compose.yml
# edit docker-compose.yml to set env vars
docker compose pull
docker compose up -d

git clone https://github.com/ftsiadimos/Web-Terminal-AI
cd Web-AI-Terminal
./start.sh          # creates venv, installs deps, starts server

Or manually:

python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env   # then edit .env
python app.py

Environment variables

Variable	Default	Description
`OLLAMA_HOST`	`http://localhost:11434`	Base URL of the Ollama API server.
`OLLAMA_MODEL`	`llama2`	Model name to use for AI responses.
`SECRET_KEY`	random	Flask session secret. Set a stable value in production.
`SETTINGS_ENC_KEY`	none	Fernet key for encrypting stored SSH passwords. Generate with `python -c "from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())"`.
`FLASK_ENV`	`production`	Set to `development` for debug reloading.
`FLASK_DEBUG`	`0`	Enable Flask debug mode (`1` = on).

Web AI Terminal v2.3.0