Forem: Stephan Coertzen

ChatGPT Desktop Client for Linux

Stephan Coertzen — Fri, 06 Mar 2026 09:35:22 +0000

If you're a Linux desktop user, you probably noticed something annoying.

There isn’t really a good native ChatGPT desktop client for Debian-based distributions like Ubuntu, Linux Mint, Pop!_OS, etc.

Yes, you can always:

Use the browser
Create a PWA
Use unofficial wrappers

But most of these either feel clunky, are outdated, or don’t integrate well with the Linux desktop experience.

So I decided to build one.

The idea

I wanted something simple:

A lightweight desktop wrapper
That works well on Linux desktops
And can be installed easily with .deb packages

The goal was not to reinvent ChatGPT, but simply provide a clean desktop experience.

So I built a small Electron-powered ChatGPT client.

👉 GitHub repo:
https://github.com/jfscoertzen/ChatGPT-client

Features

The client provides a simple desktop experience for ChatGPT:

Native Linux desktop application
Debian package support (.deb)
Works on Ubuntu, Linux Mint, and other Debian-based distros
Simple Electron wrapper
Runs ChatGPT in an isolated desktop window
No browser tabs required

It behaves like a proper desktop app instead of just another tab.

Why Electron?

Electron makes it straightforward to:

Package a web application
Create native desktop windows
Distribute binaries easily

Since ChatGPT is already a web interface, Electron is actually a very practical solution here.

Installation

If you're on a Debian-based distro:
Download the .deb from the GitHub releases.

Install it with:

sudo dpkg -i chatgpt-client.deb

Or with apt:

sudo apt install ./chatgpt-client.deb

Then launch it from your applications menu.

Why I made this

I use ChatGPT constantly while working on:

backend systems
Linux infrastructure
development tools

Opening it in a browser tab always felt a bit messy.

I wanted something that behaves like:

Slack
Discord
VS Code
Any other proper desktop tool

Now ChatGPT lives as its own desktop application.

Contributing

If you want to improve the project or add features, contributions are welcome.

Repo:
https://github.com/jfscoertzen/ChatGPT-client

Ideas for future improvements could include:

system tray support
global shortcuts
multi-account support
better packaging
Closing thoughts

Linux desktops deserve good first-class developer tools, and sometimes that means building the missing pieces ourselves.

This project is a small step toward making ChatGPT feel like a native Linux app instead of just another browser tab.

If you're a Linux user, give it a try and let me know what you think.

Introducing spec-kit: Spec-Driven Development + Ollama & OpenRouter Integration

Stephan Coertzen — Mon, 15 Sep 2025 09:27:29 +0000

Hey folks,

I’ve been working on some enhancements to spec-kit
, and I’m excited to share them with you. These updates bring in CLI, Ollama, and OpenRouter support to supercharge spec-driven dev workflows.

🔍 What is spec-kit?

Spec-kit is a toolkit for Spec-Driven Development, helping developers go from idea → spec → implementation with better alignment and iterative clarity.

It supports:

Multiple AI coding agents (Claude Code, Gemini CLI, GitHub Copilot, Cursor, etc.)

Cross-stack / tech independence: not tied to one language or framework

Lightweight requirements (Python 3.11+, Git, Linux/macOS or WSL2 on Windows, and an AI agent)

✨ What I’ve added

With my contributions, spec-kit now also allows:

CLI support: run spec-kit directly from the terminal

Ollama integration: use local LLMs as backend agents

OpenRouter support: connect to multiple hosted models with one interface

This means you can now choose fully local, fully cloud, or hybrid workflows.

🚀 Core CLI Commands

Here are some of the most useful commands to try out:

Specify your project

speckit specify

Use AI to flesh out your requirements and specs. This is where ideas become structured, testable specifications.

Generate a plan

speckit plan

Automatically generate a high-level plan of implementation steps from your specs.

Break down into tasks

speckit tasks

Turn your plan into actionable development tasks — perfect for managing iterations and team work.

⚡ Example with Ollama & OpenRouter

Run a spec using a local Ollama model

speckit specify "Write a todo list application" --ai ollama

Or use OpenRouter to run via a hosted model

speckit plan "Tech Stack: Docker, MongoDB, React, Vite, NodeJS" --ai openrouter

💡 Why this matters

Faster prototyping → from raw idea to structured plan in minutes

Flexible model choice → local (Ollama) or hosted (OpenRouter)

Better workflows → specs drive planning and tasking, not just ad-hoc coding

👀 What’s next

I’d love feedback on:

Other LLM providers to support

How you’re using Ollama / OpenRouter in practice

Improvements for the CLI flow (esp. specify → plan → tasks pipeline)

Contributions and ideas are very welcome 🙌

👉 Try it here: https://github.com/jfscoertzen/spec-kit#

New Here!

Stephan Coertzen — Tue, 12 Apr 2022 12:55:40 +0000

Hi there! I'm new here! Please checkout my new git repo that I'm working on: https://github.com/jfscoertzen/HTON