Tools: Copilot Ralph. Built a Desktop UI for GitHub Copilot.

What I Built ## GitHub Repository ## ashiqsultan / copilot-ralph ## A Desktop app to run copiot in ralph mode ## Copilot Ralph ## Download ## Requirement ## Whats included ## How it works ## Inspiration ## My Experience with GitHub Copilot CLI ## Choosing models GitHub Copilot CLI Challenge Submission This is a submission for the GitHub Copilot CLI Challenge I built a desktop app for Copilot to work on requirements in a Ralph loop mode. The app has a plan mode and also creates git commits for each task. For those who prefer video you can watch the video demo, for readers here's what you can do in the app A desktop application to vibe code using GitHub Copilot. Define your tasks in a simple UI to build them in a Ralph loop way. MacOS: Download link (universal dmg) For checksum check Releases page. You need to have copilot cli installed If not please refer GitHub Copilot CLI Installation The requirements are stored in plain JSON file Plan mode is optional, but recommended. The entire plan is sent as a single call to AI. The plan is stored for each requirement Starting the execution mode will pick the requirements one by one and build the application Original post on Ralph loop. This is the post that triggered the Ralph way to use claude code. And I thought of building an UI for this for copilot because, TBH, Copilot is the chepest pricing I could find right now for AI assisted coding. My app doesn’t strictly follow the OP, because I’ve moved some responsibilities out of the AI layer and into the orchestration layer. The system now handles the following tasks: I made this way so the system is predictable and to reduce ambiguity of relying on AI This is my first experice with AI in CLI (yes I dont have Claude code), before this I have used copilot only inside VSCode but using it in a CLI feels like more control. I liked how we can mention files with @ (which I also included in my app btw). I also loved the --yolo flag and I was mostly starting my sessions with yolo mode. Almost forgot to mention the --resume session was a saver and the information on how much premium request info at end of session was really helpful. I must say this, choosing models in copilot felt more like a survival game. As I'm in a free tier I dont want to lose all my premium requests, since my app in itself is an UI for copilot, so testing the app also means additional calls so I followed this strategy. Sonnet 4.5 for normal tasks and Opus only when required so I dont use x3 the limit. This is my typical flow If you like the project a Github Star ⭐ would be great. You can visit the webpage or Github to download and try the app. Templates let you quickly answer FAQs or store snippets for re-use. Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink. Hide child comments as well For further actions, you may consider blocking this person and/or reporting abuse - Vibe code by defining tasks - Refer files in the tasks with @fileName - Plan mode to plan your tasks before executing - Start building - View files changed in each taks in a Git view. - Each requirement runs in a separate call, to prevent llm context rot. - Git commit on each task - View files chanes on each task in git diff view - Full visibiliy on whats happening as everything is store as plain json and txt files. - Linear selection of requirements - process.txt updates after each task - Creating Git commits - Start in yolo mode - Select models based on requirement. - Choose the files I think the AI should know for the task - First the Plan mode - Then Execute mode