Fredy Acuña

Data Engineer & Sr Full stack developer

[UI/UX Savior @UiSavior]

Sites on the internet for design inspiration.

Web Design → https://t.co/IDTg0fRObK
Landing Pages → https://t.co/ulUYJp3EDf
Saas Websites → https://t.co/EacR7Liy9H
Navbar → https://t.co/1YHU4yfOxW
CTA Sections → https://t.co/bFOrpIgWIW
Animation → https://t.co/VfRAI7e5Ch
Mobile Apps → https://t.co/gxq43FqLG3
Brands → https://t.co/Q38cExyN5c
Icons → https://t.co/RyMj2EzdSM
Design Systems → https://t.co/s4MyCFjQSD

[Hasan Toor @hasantoxr]

🚨 BREAKING: CHINA just released a Python framework for building AI agents. 100% OPEN SOURCE.

It has visual agent design, MCP tools, memory, RAG, and reasoning. All built in. All working together.

It's called AgentScope.

You describe your agent system. It builds the architecture, wires the tools, and runs the whole thing. You come back and there's a working multi-agent pipeline. Not a prototype. Not a demo. The actual system.

Not a wrapper.
Not a chatbot builder.

A full Agent-Oriented Programming framework that thinks in agents from the ground up.

Here's what it does out of the box:
→ Visual agent builder so you design your entire system before writing a single line of code
→ Native MCP tool support, plug any external tool directly into any agent in your pipeline
→ Built-in memory so every agent remembers context, decisions, and history across sessions
→ RAG pipeline ready to connect your own documents, databases, and knowledge bases
→ Reasoning modules that let agents plan, reflect, and self-correct without human input
→ Multi-agent coordination so your agents collaborate as a system, not a pile of isolated API calls

Here's how it thinks:

You define your goal. AgentScope maps the agent roles. Each agent gets its tools, its memory, its reasoning layer. They coordinate. Results flow back up. You get a finished output.
A single complex task might route through a planner agent, a researcher agent, a coder agent, and a critic agent, each doing its job, then converge into one clean deliverable.

Here's the wildest part:
AgentScope is built by Alibaba DAMO Academy. The same lab behind Qwen. They didn't assemble this from existing pieces. They designed the entire framework from first principles around how agents actually need to think, remember, and work together. Most frameworks give you building blocks. AgentScope gives you an architecture. The community has already started plugging it into data pipelines, research workflows, and full automation systems the team never planned for.

100% Open Source. Apache 2.0 License.

[Matt Dancho (Business Science) @mdancho84]

Becoming a 10X engineer ain't what it used to be.

It's literally a https://t.co/PyEqUemgGu file.

Want help?

[Felipe | Robot.com @felipekiwi90]

Six months ago, we introduced https://t.co/pNoRV1JTjC

Today, we launch it 🎉

Over the past few years, we’ve quietly scaled from 300K to 1.7 million+ robotic tasks.

500+ real robots. Doing real work every day — delivering, moving, inspecting, and more.

Here's the lineup:

1. R-Dog ™ — Digital Out-of-Home Advertising (New)
A robotic dog with dual high-resolution screens, bringing motion and interactivity to advertising. And a moving tail :)

2. R-Noid ™ — Humanoids (New)
We built ours differently. Assisting in kitchens and handling repetitive work. (Not just to impress).

3. R-Kiwi ™ — Last-Mile Delivery
Delivers meals across campuses. Designed for outdoor autonomy and social acceptance.

4. R-Cargo ™ — Warehouse & Logistics
Moves materials across factories and warehouses. Built for precision and indoor/outdoor reliability.

Our advantage isn’t just technology. It’s trust.

Because in physical AI, social trust isn’t nice-to-have; it’s the moat. It’s how robotics stops feeling foreign and starts feeling familiar.

We’re here to lead by building what can be deployed and scaled now.

We’re here to show that robots can be accepted — even loved — by design.

[Akshay 🚀 @akshay_pachaar]

Google released Gemma 3 270M, a new model for hyper-efficient local AI!

We'll fine-tune this model and make it very smart at playing chess and predict the next move.

Tech stack:
- @UnslothAI for efficient fine-tuning.
- @huggingface transformers to run it locally.

Let's go! 🚀

[Rohan Paul @rohanpaul_ai]

This github repo is a goldmine.

3.4K Starts ⭐️ in 4 days.

end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for real-world launches.

[Aadit Sheth @aaditsh]

This person created a prompt that stops ChatGPT from hallucinating

[Weaviate AI Database @weaviate_io]

What is Model Context Protocol (MCP) and why is everyone building an MCP server?

Let’s break it down 👇

MCP is a new standard designed to unlock the full potential of AI models by giving them structured, dynamic access to the right context, without having to reinvent the wheel each time you need to define and serve a tool for an LLM.

MCP lets external sources feed models with:
• Background knowledge and the right context
• Real-time data
• Memory
• and more!

💡 The best part, it also standardizes how we serve and keep these services live for LLMs and other MCP clients:

An MCP server acts as a context engine—sitting between your model and any external applications or tools—delivering just the right information at the right time.

Think of it as a new standard of middleware that has the role of helping your model understand the world it’s operating in.

And, some great news on this: We already have an MCP server ready for you to use out in the wild! Including our very own Weaviate MCP server which has tools like “Weaviate Cloud collection as a knowledge base” ready for you to hook up to an LLM 💚

Check it out: https://t.co/N1hyR1O6MF

If you’re building serious AI apps—MCP is worth your attention.

[Akshay 🚀 @akshay_pachaar]

Here's the easiest way to build an MCP server:

1. Use Gitingest to convert the FastMCP repo into LLM-ready text.
2. Download the text file.
3. Upload it to Google AI Studio, specifying the MCP server type.

Gemini 2.5 Pro handles the rest!

[Fredy Acuña @Fredhii_]

@fireship_dev In my opinion, I recommend using Dokploy over Coolify.

[Luchovoltio @luchovoltios]

Uno necesitando bajar el dichoso certificado tributario y la plataforma de @PorvenirOficial lleva como una semana caída para este trámite @DIANColombia

[Ricardo Gottheil @ricardogottheil]

🚀 ¡Nuevo en la serie "Descubriendo Widgets"! Sumérgete en el Widget Icon de #Flutter y lleva tu UI al siguiente nivel. Desde íconos básicos hasta animados, te lo muestro todo. 🎨 #flutterdev @FlutterDev @EsFlutter #DescubriendoWidgets
https://t.co/nCo9Y6VEMN

[Ricardo Gottheil @ricardogottheil]

🚀 Explorando el mundo de #Flutter: Hoy vamos a desglosar las diferencias clave entre ListView y ListView.Builder, dos widgets poderosos para construir interfaces de usuario. @FlutterDev #flutterdev

🧵Hilo 👇🧵1/5

[Ricardo Gottheil @ricardogottheil]

🚀 ¡Nueva entrega en "Descubriendo Widgets"! 🔍

Profundiza en el widget Text de #Flutter: características, estilos y más. Una guía esencial para dominar este widget. #FlutterDev #DescubriendoWidgets 📱 @EsFlutter @FlutterDev

https://t.co/QRoYOwomvv

[Fredy Acuña @Fredhii_]

Ready to go for the #FlutterConfLatam 🙈

[Ricardo Gottheil @ricardogottheil]

🚀 ¡Embárcate en un viaje de documentación de código con #Flutter! Descubre 10 #consejos esenciales para hacer tu código más comprensible y mantenible. 🛠️🧠 #Tips #Coding

🧵 Hilo👇🧵1/12

[Fredy Acuña @Fredhii_]

@kaleidofos @HackersOIHEC de 55gb aprox

[OIHEC hackers @HackersOIHEC]

Base de datos de tiktok #leak https://t.co/0lKev0nH7W

[Ricardo Gottheil @ricardogottheil]

🚀 ¡Desata todo el potencial de #Flutter! Descubre cómo las extensions pueden revolucionar tu código. Desde la teoría hasta ejemplos prácticos 😁 #Dart #flutterdev @EsFlutter @FlutterDev

https://t.co/nk0EATAmJ0

[Pratham @Prathkum]

15 AI websites that will change the way you write code.