Ghost Terminal AI: Building an Offline Haunted Terminal with Qwen 2.5 & Streamlit

Description and use

A local, privacy‑preserving terminal UI powered by Qwen 2.5 7B via Ollama and Streamlit, featuring typewriter streaming, ASCII art, and persistent memory.

Problem

Create a local, privacy‑preserving AI chat interface that feels like an abandoned terminal, without relying on external APIs.

Outcome

The application delivers a nostalgic, retro terminal experience with typewriter streaming, ASCII art, and persistent memory, all running locally without external dependencies.

Workflow

• Install Ollama and pull qwen2.5:7b-instruct
• Clone the ghost‑terminal repo
• Create and activate a Python virtual environment
• Install dependencies with pip
• Run the app with streamlit run app.py
• Interact with the terminal UI in the browser

Evidence

Ghost Terminal AI is an interactive, Matrix-themed local AI chat interface powered by Ollama (Qwen 2.5 7B) and Streamlit.

Source

Local AI Engine: Powered by qwen2.5:7b-instruct running locally via Ollama.

Source

Complete Privacy & Offline Capabilities: The model runs entirely on the host machine. Zero chat data leaves the device, allowing the terminal to function fully offline without third-party server control.

Source