Jorge Eldis

66.5K posts

Jorge Eldis banner
Jorge Eldis

Jorge Eldis

@jlamigueiro

Software Developer, Python, Rust, Golang, NodeJS, MS .NET and Chess.

Katılım Ağustos 2010
2.2K Takip Edilen1.5K Takipçiler
Jorge Eldis retweetledi
Miguel Ángel Durán
Google tiene todos sus MCP oficiales en un repositorio. Con ejemplos reales y guías para desplegarlos y usarlos. Google Maps, Analytics, Gmail, Docs y más De código abierto → github.com/google/mcp
Miguel Ángel Durán tweet media
Español
10
140
955
33.5K
Jorge Eldis retweetledi
Khuyen Tran
Khuyen Tran@KhuyenTran16·
Traditional tools like Playwright rely on CSS selectors, tightly coupling your scraper to a site's HTML. When the site changes, everything breaks and needs to be rewritten. browser-use takes a different approach. You describe the goal in plain English, and an LLM decides what to click, type, and extract. In this article, I tested browser-use on two real tasks: • Finding AI stories on Hacker News and synthesizing themes • Scraping Newegg for gaming laptops with specific constraints I share the actual outputs, cost per run, and an honest breakdown of what worked and what didn't, so you can decide if it fits your use case. 🚀 Link: bit.ly/41XC1qs #Python #AIAgents #WebScraping #LLM
Khuyen Tran tweet media
English
0
1
11
209
Jorge Eldis retweetledi
Miguel Ángel Durán
¡autoskills llega a 1000 stars en GitHub en una semana! Mi proyecto para instala skills para agentes de IA según el stack tecnológico del proyecto. → github.com/midudev/autosk…
Miguel Ángel Durán tweet media
Español
28
91
1.3K
38.9K
Jorge Eldis retweetledi
Matt Dancho (Business Science)
🚨 BREAKING: Microsoft launches a free Python library that converts ANY document to Markdown Introducing Markitdown. Let me explain. 🧵
Matt Dancho (Business Science) tweet media
English
20
265
1.9K
233.3K
Jorge Eldis retweetledi
How To AI
How To AI@HowToAI_·
🚨 Someone just open-sourced a tool that converts pdfs to markdown at 100 pages per second. It's called OpenDataLoader. It runs entirely on CPU and handles complex layouts, tables, and nested structures like a senior dev 100% Free.
How To AI tweet media
English
35
330
2.6K
143.2K
Jorge Eldis retweetledi
Miguel Ángel Durán
Espectacular biblioteca con gráficas animadas en tiempo real para React. Un elemento <canvas>, sin dependencias, a 60fps. $ npm install liveline
Español
9
83
1K
31.8K
Jorge Eldis retweetledi
Vaishnavi
Vaishnavi@_vmlops·
wanted to learn Arduino but had no hardware turns out you don't need it Velxio runs Arduino, ESP32, Raspberry Pi, and RISC-V code directly in your browser.... real emulation 48+ components. no install. no account. completely free velxio.dev the hardware excuse is gone
English
12
70
467
14.7K
Jorge Eldis retweetledi
Pololu
Pololu@Pololu·
Product of the day: our @allegromicro A5984 stepper motor driver carriers are drop-in replacements for our original A4983/A4988 stepper motor driver carriers that introduced the now-ubiquitous 16-pin form factor for stepper motor drivers. The newer A5984 operates from 8-40V and can deliver up to 1.2A continuous (2A peak) per channel on our Blue Edition 4-layer boards (lower-cost versions with 2-layer PCBs and fixed current limits are also available). Grab one today for just $4.95! pololu.com/product/5340?c…
Pololu tweet media
English
1
6
52
2.3K
Jorge Eldis retweetledi
Muhammad Ayan
Muhammad Ayan@socialwithaayan·
🚨 BREAKING: Someone just built the exact tool Andrej Karpathy said someone should build. 48 hours after Karpathy posted his LLM Knowledge Bases workflow, this showed up on GitHub. It's called Graphify. One command. Any folder. Full knowledge graph. Point it at any folder. Run /graphify inside Claude Code. Walk away. Here is what comes out the other side: -> A navigable knowledge graph of everything in that folder -> An Obsidian vault with backlinked articles -> A wiki that starts at index. md and maps every concept cluster -> Plain English Q&A over your entire codebase or research folder You can ask it things like: "What calls this function?" "What connects these two concepts?" "What are the most important nodes in this project?" No vector database. No setup. No config files. The token efficiency number is what got me: 71.5x fewer tokens per query compared to reading raw files. That is not a small improvement. That is a completely different paradigm for how AI agents reason over large codebases. What it supports: -> Code in 13 programming languages -> PDFs -> Images via Claude Vision -> Markdown files Install in one line: pip install graphify && graphify install Then type /graphify in Claude Code and point it at anything. Karpathy asked. Someone delivered in 48 hours. That is the pace of 2026. Open Source. Free.
Muhammad Ayan tweet media
English
260
1.4K
12.5K
881.7K
Jorge Eldis retweetledi
Freddy Vega
Freddy Vega@freddier·
Si esto es verdad, Anthropic está a punto de cambiar el mundo. Claude Mythos es el nuevo modelo, brutalmente capaz y que ha descubierto tantos zero-day que podría ser usado como un arma contra cualquier gobierno. Pero esto es diferente: Tiene la mayor inteligencia de un modelo, con la menor cantidad de tokens usado por tarea. Es un salto GIGANTE.
Freddy Vega tweet media
Español
67
272
2.6K
160.6K
Jorge Eldis retweetledi
Pamela Fox
Pamela Fox@pamelafox·
Congrats to the Microsoft Agent Framework team for releasing 1.0.0! To celebrate, we upgraded our 50+ examples covering agents, workflows, HITL, MCP: github.com/Azure-Samples/… You can also rewatch the livestream series where we explained each example: aka.ms/pythonagents/r…
Pamela Fox tweet media
English
3
54
296
14.6K
Jorge Eldis retweetledi
DigiKey
DigiKey@digikey·
How to automate linear actuator using @Arduino & visual programming Dive deeper bit.ly/4dr5HU6
DigiKey tweet media
English
0
10
81
2.9K