Hells to the yeah! The $1k dictionary app. work on by fable. Let’s go
Rebuilt anything already built.
reverse engineer anything.
(100% open-source, 200k+ stars)
when you like a feature in someone else's app, you usually can't see how it was built because the source code isn't available. figuring it out used to mean hours jumping between 10+ specialized tools and reading machine code by hand.
REA is an open-source MCP server that hands this work to your agent. you give it an app and a question, and the agent traces the feature down to the compiled code, explains how it works, and can build a version for your own project.
how it works:
REA brings the tools reverse engineers rely on, like Ghidra, IDA and JADX, under one interface that Claude Code, Codex, Cursor and other agents can call.
your agent asks REA to inspect the app, and REA picks the right tool, runs it locally, and returns what it found along with the evidence behind each finding.
the agent then uses those findings to dig further, explain the behavior, or write and test its own version. since every claim points back to real code, the agent works from evidence instead of guessing.
what you can do with it
↳ see how a desktop app like Notion handles copy and paste, from the button you click to the code that runs behind it.
↳ look inside compiled programs and games to understand the logic they were built on.
↳ break down Android apps into readable code to see how a feature is put together.
↳ inspect how a website is structured and what it sends over the network.
↳ examine device firmware, network recordings and other files that were never meant to be read by people.
in one of their showcases, it rebuilt a sound function from the old DX-Ball game that compiles back to the exact same code as the original.
everything runs on your machine, and setup adds it to your agent with a single command: 𝗻𝗽𝘅 𝗿𝗲𝗮-𝗮𝗴𝗲𝗻𝘁𝘀 𝘀𝗲𝘁𝘂𝗽
it's meant for software you own or are authorized to analyze.
repo: github.com/morluto/rea
a while back, i wrote about two gaps in Claude Code. it only gets a summary when it reads a web page instead of the full content, and it can't see the full state of your backend. adding the right skills fixes both.
REA builds on that same setup and covers one more gap, since your agent can now understand apps it never had the source code for.
the full article is in the quoted post below.
Game show idea AI hackathon with live betting. There is this amazing team here at @MLHacks in NY. Hope they win!!!
Just saw Star Trek The Motion Picture. Do you think Claude or OpenAI would want to fuse with Humans?
Opus 5.5 is incredible at HTML and animations. Just amazing. Frontend Animations and Designers are now on crack
agents been working all day, i am at 12% of my weekly usage. I need to be at 100% by Wednesday. what do I do?
Just sitting casually in my room doing stuff and then suddenly I hear my home lab go Waaaaghhh! My agents are doing things!
I shouldn't dwell on how people, think and act ,and ruminate on this. We all have troubles of our own.
got to learn the price of building something
Replying to @Byte0fCode
Yes, just to play around as part of validating app ideas. I use Astro more now, haha.
Lesson learned: you can replace a SaaS for yourself, but then you have to maintain and update it too on top of everything else.
Yeah this is true
I read 40 books on startups and learned nothing.
I used to read book after book on startups. Every time someone recommended something, I'd tack it onto an ever-regenerating list of media to consume. I got nowhere, and I learned nothing.
Because learning is not reading a book, listening to a podcast, or sitting in class. Learning is when you digest information and then implement it.
If a professor teaches you that price is a signal, you haven't learned anything until you price your product too low and watch people scoff at you.
And here's the real danger of reading: too many inputs paralyze you. Advice conflicts from one source to the next, and you can't tell what to listen to because you've never acted on any of it.
So I stole a rule from @AlexHormozi : after you consume a piece of media, do everything it said before consuming another.
This is how you learn: by doing.
LOL was just talking about spending $1,800. But i haven't gotten a GPU or and thing yet..... yet.....
Just spent a Grand on some more hard drive space and RAM. Man hardware prices these days are so high
jake cukjati retweeted
112 agents, 16 hours, 60,000 lines of code. Jake Cukjati (@Byte0fCode) says stop prompting agents to code and hand them specs instead. #AIMUG youtube.com/watch?v=-65TrkDP…













