Choosing a no-code AI app builder for a small MIDI controller utility?

I’m in Portland and build expressive MIDI controllers as a side project, mostly for my own band and a couple of local electronic musicians. I want a simple companion app that reads controller data and shows mapped parameters, but I don’t write much code. The app builder comparison I came across lists options with AI-assisted prompts, drag-and-drop screens, and export limits, which sounds helpful but also a little opaque about how the generated apps handle real-time MIDI input.

My concern is whether these tools can talk to Web MIDI or Bluetooth MIDI reliably, or if I’d be stuck with a static mockup. I also don’t want something that locks down the code if I later want to tweak it myself. Budget is modest since this is a hobby, not a product launch.

Has anyone here used a no-code or AI app builder for a controller companion tool? I’d like to hear what worked and what got in the way, especially around MIDI permissions.

Update after reading more - (MOD EDIT, please no potential ad links…) kept coming up while I was checking export options. Still not sure any of them handle Web MIDI permissions reliably, so I’m leaning toward testing one cheaply before committing.

Perhaps, just try it out? I am confident that it will work, when you can describe well enough what you want.
If you have fitting hardware (an at least 16, better 24 or more GB VRAM GPU or shared memory Mac) you can try a local LLM. They are not as intelligent as frontier models but it’s free (when you have the hardware already), so worth a try. oMLX (for a recent Mac) or LMStudio (Mac, Windows or Linux) + Qwen 3.8 27b (or 4 once it’s out) or Strata + Qwen 3.8 Flash Next + opencode + would be a good start for that.
Or a 20 or 100 Euro abo of Claude or GPT. These are way better atm. for more complex tasks and don’t require powerful local hardware. Particularly the 100€ subscription, even though not cheap, gets you a long way and gives access to the best models (equivalent to several thousand Euro in tokens. I would assume that these abos will get more expensive and/or contain less compute once OpenAI/Anthropic have the market coverage they need. So, available as long as it lasts.)

Web MIDI / Bluetooth MIDI are both established apis… reliability is likely to be more dependent on your hardware and drivers than the ‘app’ that uses them. similarly, permissions are down to that api or OS, and AI support should be fine.
(ofc, AI can have hallucinations for any api, its never 100%)

Im not really sure what you are trying to do. that needs you to write/generate code…
“I want a simple companion app that reads controller data and shows mapped parameters”
sounds like something you could just get an app for, rather than create your own.

sure vibe coding is the buzz for now, but still many good reasons use something that someone else has not only created, but tested and supports.

if you want to go down this rabbit hole… thats cool too, it can be fun…

if you are using a ‘app builder’, and it generates code, then you could always use that as starting point, then point an LLM at the result to tweak it if necessary (for something the app builder doesn’t support)

however, I’d test this beforehand, its possible for code to be ‘obfuscated’ (made hard to read), whilst this doesn’t make it impossible for AI to process, it can make it quite a bit harder (= spend more tokens!) .
Im not sure this is common practice (for AI apps, it is for pro apps) at the moment, but I expect it will, given the popularity of vibe coding :wink:

or as @NothanUmber said, just vibe code it from scratch if you have a clear idea what you want, scope is limited etc… just becareful, its easy to end up deeper you expect at the outset… which can be fun - if its something you enjoy (and dont mind spending tokens / $)

as for LLM,
I think local stuff is either very expensive, or pretty limiting.

Claude’s ‘cheap’ sub (20$) , I found too limiting to be useful… and from what I hear, even the $100 is easy to burn thru.

I personally (after copilots repricing) settled on opencode mostly zen, but also supports with byok… you could use opencode/go for simple stuff…
I use a variety of models, though Deepseek variants I guess is main one.

What I like about this is. you don’t hit session limits as you are paying by the token.
also, $20 is a lot of tokens if you are selective with models,
then factor in you are often paying for subs when you are not that active.

I think what I like most though, is model selection and ‘token’ management are good skills to learn. both for frontier models, and also later for local llms.

as @NothanUmber alluded too, I think the days of cheap LLMs and subs is limited,
Github copilot used to be crazy good value at $10/month, and now is much more expensive.
Claude, seems to have kept its price stable, but you get much less for it, as I said $20 i found almost unusable.

Not too surprising really, costs are going up, and also Id assume the corp market is going to be their main cusstomers - and they have AI budgets.

so unfortunately, I think hobbyists/vibe coder have started to get priced out the market.
possibly, local LLMs will be the future for them, but with hardware costs (RAM/GPU) at an all time high, probably not for next year or so…

but hey, ride the wave - its fun times :wink: