Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

OCTOBER’S MOST TRENDING GITHUB REPO: REA (Reverse Engineer Anything). 86.7K ⭐️ on GitHub, +25K just today. It lets your AI agent take apart almost any app and tell you how it works. Free and open source. Here’s the idea: You see a feature you like in some app. You...

50,644 Aufrufe • vor 15 Tagen •via X (Twitter)

51 Kommentare

Profilbild von tobarra
tobarravor 15 Tagen

github está on fire con esto

Profilbild von céline ✧
céline ✧vor 15 Tagen

absolutely

Profilbild von angel
angelvor 15 Tagen

wait what this is insane

Profilbild von céline ✧
céline ✧vor 15 Tagen

ong!

Profilbild von ryu.
ryu.vor 15 Tagen

como?? madre mia , esta repo es una completa locura

Profilbild von céline ✧
céline ✧vor 15 Tagen

yess

Profilbild von karla
karlavor 15 Tagen

reverse engineering speedrun any%

Profilbild von Alba
Albavor 15 Tagen

no source code needed is actually wild

Profilbild von céline ✧
céline ✧vor 15 Tagen

i know!!

Profilbild von rob.
rob.vor 15 Tagen

puedo usarlo con discord?

Profilbild von céline ✧
céline ✧vor 15 Tagen

yes, i used it with discord yesterday

Profilbild von HawksT
HawksTvor 15 Tagen

wonder how long until apps start shipping obfuscation just to slow down agents lol

Profilbild von draven
dravenvor 15 Tagen

86.7k stars for a reason

Profilbild von céline ✧
céline ✧vor 15 Tagen

absolutely

Profilbild von Marco
Marcovor 15 Tagen

+25k estrellas en un dia, la verdad que poco me parece para esta locura

Profilbild von céline ✧
céline ✧vor 15 Tagen

so real

Profilbild von yuulia ✟
yuulia ✟vor 15 Tagen

this is crazy crazy

Profilbild von Vivi
Vivivor 15 Tagen

esto es brujería pero legal

Profilbild von céline ✧
céline ✧vor 15 Tagen

hahahah

Profilbild von MS.¥
MS.¥vor 15 Tagen

esto es brujería pero legal

Profilbild von céline ✧
céline ✧vor 15 Tagen

😂😂

Profilbild von Ryoru 𒌐
Ryoru 𒌐vor 15 Tagen

bookmarked, testing it tonight

Profilbild von céline ✧
céline ✧vor 15 Tagen

lmk

Profilbild von brenz.
brenz.vor 15 Tagen

lo probare

Profilbild von céline ✧
céline ✧vor 15 Tagen

lmk!!

Profilbild von SONIA
SONIAvor 15 Tagen

normal que este trending esto es loco

Profilbild von céline ✧
céline ✧vor 15 Tagen

yess

Profilbild von gus
gusvor 15 Tagen

ok this is lowkey genius

Profilbild von céline ✧
céline ✧vor 15 Tagen

its so alpha

Profilbild von Kevin Moreira
Kevin Moreiravor 15 Tagen

devs about to learn so much from this

Profilbild von céline ✧
céline ✧vor 15 Tagen

fr!

Profilbild von ronix
ronixvor 15 Tagen

esto es como tener rayos x para apps

Profilbild von céline ✧
céline ✧vor 15 Tagen

Hahahah literally

Profilbild von toba
tobavor 15 Tagen

everything staying local is the best part

Profilbild von céline ✧
céline ✧vor 15 Tagen

yess tbh

Profilbild von adri
adrivor 15 Tagen

finally i can stop guessing how apps work

Profilbild von Paulo Pierrondi | AI agents in production
Paulo Pierrondi | AI agents in productionvor 15 Tagen

Reading how an app works was never the moat. The moat is what a reverse-engineer can't see: the data, the support history, the approvals that decide what ships. Cloning a feature is a weekend now. Running it reliably for a year still isn't.

Profilbild von David Arnal
David Arnalvor 15 Tagen

The “show me the proof” part is what stands out. Can it reliably distinguish observed behavior from an educated guess when the app’s internals are opaque?

Profilbild von E_genius
E_geniusvor 15 Tagen

+25k stars in a day for a tool that takes apart any app. every saas founder reading this just felt their moat get a little shallower lol

Profilbild von rachit
rachitvor 15 Tagen

saved

Profilbild von berni
bernivor 15 Tagen

free and open source? say less

Profilbild von naldz.
naldz.vor 15 Tagen

me opening discord just to understand the typing dots

Profilbild von céline ✧
céline ✧vor 15 Tagen

me too hahah

Profilbild von kai.
kai.vor 15 Tagen

claude code con esto es otro nivel

Profilbild von Paulo Pierrondi | AI agents in production
Paulo Pierrondi | AI agents in productionvor 14 Tagen

Agents that can take apart any app are powerful, so the permission layer matters. Mine can inspect and propose all day, but anything that writes or sends goes through me.

Profilbild von CesarAG
CesarAGvor 15 Tagen

my agent about to know discord better than discord devs

Profilbild von BNELLY
BNELLYvor 15 Tagen

saved

Profilbild von ari.
ari.vor 15 Tagen

this is how you actually learn to code

Profilbild von catman
catmanvor 15 Tagen

REA can inspect Mac, Linux, Windows, Android apps, Electron apps, and websites, while keeping the analysis on your computer; that helps explain behavior without handing over source code.

Profilbild von 小明叔叔看AI · Uncle Xiaoming
小明叔叔看AI · Uncle Xiaomingvor 14 Tagen

The most interesting part isn't the reverse engineering — it's that REA turns every proprietary app into a free textbook. Your competitors' UX decisions, their API design, their edge cases: suddenly all readable. The real moat was never the code itself, it was the "how it works" knowledge locked inside. REA just turned that knowledge into a commodity.

Profilbild von Ahmad
Ahmadvor 15 Tagen

people are gonna take apart so many apps with this

Ähnliche Videos

WHAT IS AN AI "SOFTWARE FACTORY" AND IS IT HYPE (31 MINUTE BREAKDOWN) I think it's a silly name for a genuinely USEFUL idea! A software factory is 5-6 markdown files that sit next to your code and tell your agents how you like to work, so you can build high quality apps 24/7. It's going viral because AI coding has a trust problem. The model can build the feature, but with no structure around it you end up babysitting the agent, wondering what changed and hoping it didn't break something important. So you build with agents the same way a factory builds physical products! 1. Each feature gets its own station, which in software means its own branch, so multiple agents can work at the same time without stepping on each other. 2. The build station gives the agent rules for how to write the code, because "it works" is very different from "a developer could open this repo next month and understand what happened." 3. The proof station makes the agent show evidence. Screenshots, videos, speed numbers, before-and-after states. It has to prove the thing works instead of saying it works. 4. The review station runs the work through a code review agent, and if it doesn't clear the bar, it goes back through the line. 5. Then you show up at the end to merge. For a 100+ years people have run production this way, and it worked because the structure is good. The full episode on what’s a software factory is NOW live on The Startup Ideas Podcast (SIP) 🧃 with the wonderful Micky Watch: So is it hype?!? I don't think it is, because of what it does to your output! WITHOUT a factory, you build ONE feature at a time and you're the bottleneck at every step, prompting, checking the diff, testing it yourself, hoping nothing else broke (spoiler alert it often does). WITH a factory, EACH feature runs in its own isolated copy of the app, so you can have 10+ of them going at once, and each agent has to prove its own work and pass a code review before it ever reaches you. Instead of supervising the work, you're APPROVING finished work that already has evidence attached. REALLY interesting to see how work with agents is evolving to be….well, similar to working with people!

GREG ISENBERG

32,056 Aufrufe • vor 1 Monat