Open-source personal finance app.

Lord Prompts es un GPT que mejora la calidad de tus prompts para que obtengas mejores resultados! Utiliza como base el libro público de Gemini que explica como crear prompts que le saquen jugo a la AI Les dejo algunos ejemplos en este 🧵 chatgpt.com/g/g-6884313ae4…

Commands for automating Claude Code CLI tasks and dev workflows

This is the fastest serving engine for LLMs! LMCache cuts time-to-first-token by 7x and slashes GPU costs dramatically. Think of it as a smart caching layer that remembers everything your LLM has processed before. 100% open-source, makes vLLM go brr...

Manus shared an article on how they manage the context of their agents. It actually includes some pretty practical point. If you’re building or using agents in any sort or form, this can be quite useful.

🧠 LangGraph Deep Dive Learn to build multi-agent AI systems with LangGraph, featuring human-in-the-loop processes and advanced memory management. Implement knowledge graphs and coordinate multiple agents in complex workflows. 📺 Watch the technical tutorial:

🐶 🤖 DataPup: AI Database Client A modern database client powered by LangChain agents for intelligent query assistance. Starting with ClickHouse, DataPup brings AI-powered management to databases, with PostgreSQL and MySQL support coming soon. Check it out! 🚀

🤖🌐 ParserGPT: Smart Web Scraping Transform messy websites into clean CSV data using LLMs and deterministic rules. Powered by LangChain and LangGraph, ParserGPT learns website structures once to enable efficient, repeated data extraction. Learn more about ParserGPT:

1. Spec Driven Development y Prueba con spec kit Como vibe codear de forma realmente escalable / para enterprise x.com/juliandeangeIi…

2. Claude Code subagents + MCP Playwright Un poco de como funcionan los subagents y una poc usando el MCP de playwright x.com/juliandeangeIi…

Manus was one of the few experiences for me that showed what can be achieved with well-designed agent architecture. As Yichao 'Peak' Ji mentioned in the LangChain webinar, they have changed the agent design several times, so their learnings in context engineering are very valuable.

Deep Agents represent a shift in how AI systems operate – unlike simple chatbots or basic RAG applications, these agents run for extended periods, execute multiple sub-tasks, and make complex decisions autonomously. In this webinar, we'll dive into practical approaches for

Cada vez que salía 008 en pantalla 🫩 #StrangerThings5

"Los médicos le dieron seis meses de vida. Cáncer de pulmón en etapa terminal. El griego Stamatis Moraitis 🇬🇷vivía en Estados Unidos cuando recibió el diagnóstico. Al salir del hospital, no pensó solo en la muerte, pensó en algo más simple y práctico: Si muero en EEUU, mi funeral

HELLFIRE LIVES!!!!!!!!!!!

Los que crecimos con Harry Potter nunca pensamos que volveríamos a experimentar algo así. Ver un grupo de niños formar amistades, unirse para derrotar el mal, crecer ante nuestros ojos… Stranger Things ha marcado a toda una generación y decir adiós duele. #StrangerThings5

Tendencias Pero son pelotudos? En 2 cap anteriores Derek dice que Mike ahora es su mejor amigo, no es tan difícil Miren las series sin el teléfono en la mano y presten atención

x.com/i/article/2012…

Thanks to good people at Anthropic we now have an official MCP for Excalidraw! Take it for a spin on Claude (search for Excalidraw in Connectors, or use in Claude Code and elsewhere). More to come. ✌

MCP Servers Are Coming to the Web. MCP lets AI agents call tools on backends. WebMCP brings the same idea to the frontend, letting developers expose their website's functionality as structured tools using plain JavaScript (or even HTML), no separate server needed. Instead of