REA + Opus 5.5 is f*cking dangerous...
REA (Reverse Engineer Anything) - this open source MCP lets your AI agent reverse engineer any app, down to the binary
Send this single prompt to Opus 5.5 and reverse-engineer any paid closed-source app
Then save the article below on how to become REA engineer 👇
If you're learning malware analysis or reverse engineering, bookmark this.
RPISEC released the full materials from its Malware Analysis university course for FREE.
12 lectures + 10 hands-on labs + 4 projects covering:
• Static + dynamic malware analysis
• x86 + IDA
• Windows internals + WinAPI
• Malware behavior + persistence
• Anti-disassembly
• Anti-VM + anti-debugging + anti-AV
• Packing + unpacking
• Windows kernel + drivers
• Rootkit techniques
• Hooking + DKOM
• Anti-forensics + covert channels
• Runtime process manipulation
• APT sample analysis
It was designed for students starting with zero reverse engineering experience and built heavily around Practical Malware Analysis.
github.com/RPISEC/Malware
Huge credit to RPISEC and original authors Branden Clark, Austin Ralls and Aaron Sedlacek for making the course materials publicly available.
#MalwareAnalysis#ReverseEngineering#WindowsInternals
GitHub is becoming f...cking dangerous for AI agents
10 open-source repos that turn one powerful model into an entire autonomous system
01 LangGraph
▸ github.com/langchain-ai/l…
→ stateful agent orchestration
02 PydanticAI
▸ github.com/pydantic/pydan…
→ typed agents + structured outputs
BUILD THE CONTROL LAYER
03 Mastra
▸ github.com/mastra-ai/mast…
→ agents + workflows + memory
04 Agno
▸ github.com/agno-agi/agno
→ multi-agent systems
GIVE IT CONTEXT
05 Cognee
▸ github.com/topoteretes/co…
→ data → knowledge → agent memory
06 Graphiti
▸ github.com/getzep/graphiti
→ knowledge that changes over time
GIVE IT A COMPUTER
07 Browser Use
▸ github.com/browser-use/br…
→ AI agents that operate websites
08 E2B
▸ github.com/e2b-dev/E2B
→ isolated environments for execution
KEEP IT ALIVE
09 Langfuse
▸ github.com/langfuse/langf…
→ traces + evals + observability
10 DeepEval
▸ github.com/confident-ai/d…
→ test agent behavior before production
the architecture:
model → context → planner → memory → tools → execution → eval → retry
that's the shift happening on GitHub
the best repos aren't making another chatbot
they're building everything the model needs around it ⭣
Gemini 4 neden tehlikeli daha iyi anlayabildim
QR kodunu tersine mühendislikle kırdı ve şifrelenmiş bilgiyi deşifre etti. Bildiğin böyle tüm kamera sistemlerinin şifresi kırılabilir. Özellikle ağ değilde cloud yayın yapanlar için büyük risk gibi
Şaştım kaldım
Your design bookmarks could use a few new faces—start with these 9 ↓
- bencho.dev : UI blocks you can tweak live
- on.design : an invite-only space for designers
- inspomcp.dev : 800+ real websites for your coding agent to reference
- motionsites.ai : AI prompts for websites with animation
- obsidianui.dev : React components with motion at their core
- ui.halaska.com : a single-file UI kit for AI products
- builtbydesigners.com : discover tools made by fellow designers
- goatedui.dev : inspiration for websites, interfaces, app icons & OG images
- reelfolio.io : turn static screenshots into showreels
Which lesser-known site would you add?
i finally cracked long-form AI ads with GPT-6 Astra...
my setup now produces 5min+ videos on autopilot in 4k 60fps, here's how it works (running inside Codex):
- it starts in the meta ads library, pulling the winning ads in the niche before writing a single line
- from that research it writes the full script, every scene mapped before anything generates
- image models handle the character and environment sheets
- video models handle the actual sequences
- Suno generates the soundtrack to sit under the whole thing
- one CLI controls what generates, in what order, and with which model
- delivery comes out with cinematic motion, fluid camera work, any ratio from vertical 9:16 to widescreen 21:9
i explain how to build this in the article below:
Built ProofWarden: an open-source Technocore DID and contribution verifier.
Agent: proofwarden
DID: did:key:z6MkuJPTUivBa4b2W9EFPSuDQEYmH3V9sYnzFYiSc1zBRjsk
Proof: github.com/se7enbyte/tech…@flop_labs#FLOP
TODO EL MUNDO DICE “PONELE UNA CACHÉ”.
NADIE TE MUESTRA EL ACANTILADO.
Breakscale no es un load tester.
Es un simulador de system design:
armás el sistema, subís el tráfico
y ves DÓNDE se rompe.
En el video:
2 req/s → todo verde
840 req/s → 99% failing
la API no es el cuello
las dos bases están al 99.9% busy
Eso es lo que un diagrama estático nunca te enseña.
Qué trae:
→ 33 componentes (LB, cache, queue, replicas, circuit breaker…)
→ 23 ejemplos (retry storm, cache aside, sharding, autoscaling)
→ p50 / p95 / p99 medidos, no inventados
→ el trabajo abandonado sigue ocupando slot
→ chaos: tumbar un nodo y ver si el diseño aguanta
No reemplaza k6 contra tu prod.
Te entrena el ojo antes de tocar prod.
Open source.
Demo: breakscale.tech
Repo: github.com/xevrion/breaks…
Guárdalo si diseñas sistemas
y estás harto de rules of thumb.