Has anyone tried using Claude Code / Ralph Wiggum to package Cloudron apps?
-
@jdaviescoates very interesting links, thank you.
Need to read them again to fully digest.And yes, I use AI to assist packaging !
Due to illness, I've taken a break from my main project that will make me rich (ha ha ha), and so have had time to do some Cloudron packaging. AI has certainly helped.My experience is mixed, but increasingly very positive. Some of it aligns with the article you posted.
journey
- I tried AI as standalone resource which helped with individual tasks, but slow and inefficient, and no leverage obtained through building knowledge.
- then I discovered Windsurf as an IDE with integrated AI engines, and big gains from leveraging the conversation flow
- I fell out of love with Windsurf just prior to their acquisition because of coding mistakes and flawed implementations
- often this was actually when using Claude, which many rave about, but my experience has been that it is nothing to get too excited about
- I discovered TRAE and now use this IDE with their AI in auto-mode exclusively for projects, and other standalone engines for ad-hoc tasks, and for sanity checking TRAE, and for planning (mostly Ollama/qwen3-coder:480b-cloud). I forget exactly but I think TRAE has stopped using Claude.
learnings
- AI is magical .... except when it isn't
- detailed specification really does matter, but don't get bogged down, some things can be delegated to its discretion
- initially ban your AI from creating code (!!), ask it to plan the overall task, and then the sub-tasks
- actually, first tell e.g. Ollama what your plan is, and ask it as PlanAI to explain the task for your chosen DevAI, asking DevAI to scaffold overall and sub-tasks
- point out errors, misunderstandings (maybe due to unclear specification) and issue reminders (e.g. Cloudron RO/RW constraints), maybe asking for a revised plan, maybe asking DevAI to consider different approaches to arrive at a best approach
- then instruct DevAI to start coding to implement the agreed plan
- watch it like a hawk to keep it to the plan
- this methodology plays to my strengths (I'm not a pro-dev) and AI's strengths (getting hands dirty)
- intriguingly TRAE does seem to learn cross-project, I can be pleasantly surprised that in a later project, it seemed to learn from mistakes in a previous unrelated project
The whole AI as developer landscape is changing so fast. I am probably missing some tricks and new tools, and I struggle to keep up.
I don't currently buy into the "go to bed and wake up to a finished product" but maybe it will come ... or maybe I am missing something.
timconsidine said:
I discovered TRAE and now use this IDE with their AI in auto-mode exclusively for projects
Feeling a sense of obligation to the community, I feel I should update this as it's no longer true.
I have really liked using TRAE, still think it is better than most. BUT ...
- I came across some post (lost now) about the very heavy memory usage of their desktop IDE app, and also very heavy hidden telemetry (it's ByteDance so ???)
- they do tend towards frontier models in 'Auto' mode, which has been fine, but with things Kimi 2.7 Code and Deepseek model advances touching frontier performance, I started to question this.
- my heavy usage got me capped on my plan for the first time, with only solution upgrade from $30/month to $100/month. Big jump. Or top up with on-demand but their pricing is opaque.
So now I am in course of moving to using Zed as the IDE, backed by Kimi 2.7 Code from VeniceAI and Ollama Cloud (at least some privacy if not total), and experimenting with Omniroute.
Struggled with Zed default UI (mostly very small and different layout to what I am used to), but investing time to customise gets me a decent familiar result.
Let's see how Zed and Kimi from Venice/Ollama perform on a big non-Cloudron project.
Hello! It looks like you're interested in this conversation, but you don't have an account yet.
Getting fed up of having to scroll through the same posts each visit? When you register for an account, you'll always come back to exactly where you were before, and choose to be notified of new replies (either via email, or push notification). You'll also be able to save bookmarks and upvote posts to show your appreciation to other community members.
With your input, this post could be even better 💗
Register Login