Reverse Engineer Any App with AI: REA GitHub Tutorial

If you want to reverse-engineer any applications with AI that has the highest accuracy, well, you got to check

out this repository called reverse-engineer-anything. This repository has got over 60,000

stars on GitHub just a couple days after this repository has released. And people were actually able to cloning any

application using this like Adobe Premiere's and Photoshop and so many more. And the most interesting part here

is that it's able to reverse-engineer any applications like desktop applications, games, web applications,

even mobile applications, and so much more. So, that's why in this video I'm going to show exactly what is REA, how

does it work behind the scene, and also walk you through how I was able to clone a Whisper flow, which is something that

I'm currently using every single day, and try to clone it exactly the same. So, with that being said, if you're

interested, let's get into the video. Now, really quickly, what is REA? Well, REA right here you can see it stands for

reverse-engineer-anything. And just like what it says in the description, let's say you see a feature

that you like. It could be a desktop applications, web applications, or a mobile applications. It will get down to

the binary level, understand exactly how this application works, and giving AI much more context to build a much actual

results. Now, in the past we already have something like spec-driven development before, right? Which we know

that if we were to have AI here to building applications with the highest accuracy, we need to have more context.

And that context is really the key. And that's exactly what REA is trying to do. If you want to have a clone anything,

well, you got to give more context. You got to give more evidence on exactly what this application works behind scene

to getting more accuracy in terms of the actual building process. Now, essentially the way how it works for REA

is you can treat it as like a skill. And this skill here has many MCPs. Like for example, Hopper for desktop, JavaScript

or browser here for web applications, maybe there's mobile applications, hardwares, and so many MCPs. And REA

here is a skill that teach AI agent on how to using these tools and try to collecting informations from those

applications itself. All right. So, now you know exactly what is REA and how does it work behind scene, let's take a

look at how we can use it to set it up and actually use it to see what is the accuracy result look like when it comes

to cloning an existing applications that I'm currently using every single day. All right, so the first step we're going

to do here is to run this command inside of our repo. Now, before you do so though, I highly recommend to check your

current node version. Simply just type in node -v and it's going to tell you exactly the current version you're using

inside of your node.js. Now, the requirement for this is that you have to be above 24, so version 24 above. And if

you want to upgrade it, so simply just type in brew upgrade node and it's going to upgrade that to the latest version.

So, once you have the latest version for node, simply just copy this command right here and what you're going to do

here is going to come back to your terminal, paste that command and it's going to run it.

So, what's going to happen here is it's going to install this onto your local machine. First of all, we're just going

to pick the ideal AI agent you're using, so I'm choosing claw code and codex. So, feel free to choosing open code or any

other AI agent harness you want. So, once you are done that and then that's what we have here is the install hopper

here for deep binary analysis. Now, you can think of hopper here is kind of like a third-party tool, right? That this REV

here uses or REA, sorry, uses that basically just try to analyze exactly what this application do, right? So,

usually the way how it works is developer writes a source code and then this source code here makes the

application work. Well, because we're trying to reverse engineer this, so it's going to using a tool called hopper here

to actually analyze the applications and turning this application requirements into proper so that we can be able to

using our AI agent here to kind of reverse engineer it and try to build that out, right? So, in this case we're

going to say yes and we're going to say install this and then you can see here that right now it's asking for applying

for five different changes. So, installing the hopper deep analysis providers as well as adding claw code,

codex, whatever coding agents you have and also reverse engineering skills. So, in this case I'm going to say yes, apply

for to both and it's going to go ahead and do that. Now, right away you can see that it's going to pop out this Hopper

Disassembler, and you can see that we simply just click on try the demo, and it's going to have everything good to

go. I'm going to say check automatically here, and then what's going to happen here, you can see we have everything's

are fully installed, right? So, you can see the deeper analysis here, granted, reverse engineer, pretty much

everything's are good to go. Now, before we continue, I recently launched our school community where I

help you to master AI agents, automations, and building real AI products. This is coming from someone

who used to work as a senior AI software engineer at companies like Amazon and Microsoft. And in this community, you're

going to get full AI builder roadmap where you're going to start with AI automations, then later on moving into

AI agents, research systems, SaaS buildings, and eventually how to productize and market your AI skills.

You're going to get the templates, workflows, weekly live calls, and direct community supports. So, when you get

stuck, you can ask questions and get help right away. And the goal here is not just watch more videos. It's

actually build, post your progress, give feedback, and start to level up. So, if you're interested, make sure you jump

right in, start the first course, and I'll see you in a community. So, now what we can do here is we can

open our claw code and maybe we just explain any applications, and it's going to basically try to show the evidence on

how to reverse engineer and build that application out. So, in this case, I'm going to clear the terminal and type in

claw here, and now you can see we have our claw code. So, what we're going to do here is I'm going to just try to give

it a prompt, and let's try to see how we can be able to clone it. Now, the application we're trying to clone here

is called Whisper Flow. Now, it's a voice-to-text AI applications, and it lives on my desktop app. So,

essentially, you can see that this icon right here, if I click on it or if I do a hotkey, it's just going to

automatically try to translate, right? Try to translate any speech that I say into proper text. And it's also able to

translate meeting notes, right? So, those are really helpful. So, what I want to do here is I want to kind of

like using that skill, and see if we can be able to actually reverse engineer applications on my local machine. And

right here you can see I have prepared a prompt. It's called find Whisper flow on my entire desktop app, right desktop

folder. Use RE here to basically inspect the app and use the official website as the background. And also explain what

you can be approved from the application files, right things like that. And here's to get a small working version

here working. So, I'm going to basically open my Claude here and paste the prompts, and just send it over, and let

Claude here do do the rest. So, in this case, I'm going to let it go, and let's see what it does. All right, so now you

can see that once we have our application is fully complete here, if I were to open the app, here is what it

looks like. So, we have the exact clone of Whisper flow right here in my desktop app. So, you can see that currently we

have all the conversation, everything that I said is inside of this. I can also click on note taker here to see the

past notes that I have took, right? So, I can view the entire transcript or resume if I want to.

And I can also be able to start to using a shortcut, right a short key. So, I'm going to type in the short key right

here, which is option plus one. So, I want to start a new application. And you can see that we have the text

here showing, okay? And I can say different languages, like uh "Jintian shi Zhouliu."

So, you can see that we have English and Chinese here also in the same uh input, right? So, we can be able to also have

the ability here do that. And also it's really, really fast. So, it's not like, you know, it takes a long time here to

load. It's transcribed locally on my machine, so the conversation or the voice here does not go on the internet,

which you can see here, okay? So, as you can see that it's actually able to using reverse engineering tool here to analyze

exactly how it works. And you can see that it's able to creating a similar versions of this using our AI agents.

All right, so pretty much that's it for this video on the preview for REA, what it is, how it works, and how you can be

able to set it up. Now, the last part what I want to talk about here is just my take, my my two cents on this. I feel

like this is going to be really revolutionary because now the application here, the code, is no longer

the moat. The moat is actually the brand and the actual users, right? The actual data is the moat. And you can see that

this is a clear example. We have something called Photo Graph, which is going viral recently. And essentially

what this application do is cloning the entire suite, right, of Adobe Premiere, Adobe Photoshop, everything from Adobe

suites, and basically try to clone that using entirely in Rust. And you know Rust is actually a lot faster than any

other languages, and it's able to do this, right, one to one with a lot of tools that we're currently using every

single day. And I think that's something that you also have to consider. And one more thing that you have to consider

here is building better marketing, building better brands. Because if you have a stronger brand, you that's

something that they cannot be able to take away, right? So, building better brands, marketing, building

applications, and how you can really scale your business, these are things that we talk about inside of our school

community for every tech head builders. And of course, if you want to network with other business owners and

professionals, this community here can also help you do so. Now, if you're interested for this, I'll make sure to

put the school community link in the description below. And of course, if you're looking to scale your marketing

for your business, you can check out this video right here. I have reviewed 40 different skills for marketing. And

of course, if you're interested for more content like this, make sure to subscribe to this channel, like this

video, and I'll see you in the next video.