Aarón López Sosa 💻

Algo está pasando en Villahermosa. 🧵👇 Ayer organizamos el primer Café Cursor y pasó lo que muchos creían imposible: la comunidad tech salió de sus casas para conectar, debatir y crear. No solo queremos aprender; queremos que Tabasco sea referente. (Abro hilo con fotos 📸)

Announcing OpenCode School! A free, self-paced course that teaches you how to use OpenCode, the open-source AI coding agent. No account required. No personal data collected. Free forever. opencode.school

🚨 A free GitHub repo just became the best place to learn AI agent development in 2026. 70+ working projects. Every framework. Every pattern. All copy-paste ready. It's called Awesome AI Apps and it covers everything from a 3-line weather bot all the way to multi-agent pipelines running autonomous financial research. The structure is what makes it different from every other "awesome list" out there. These aren't just links to other repos. Each project inside is a self-contained, runnable example with its own README, environment setup, and code you can clone and run today. → 13 starter agents across frameworks so you can pick the one that fits your stack → 12 MCP integration examples including a hotel finder, a GitHub analyzer, and a Docker sandbox agent → 12 memory agents that retain context across sessions for tasks like job searching, social media, and brand monitoring → 11 RAG applications including one that uses GPT-5 for agentic retrieval → 14 advanced agents including a car finder, a smart GTM planner, and a conference talk generator Plus a full 8-lesson AWS Strands course baked directly into the repo with video playlists linked. github.com/Arindam200/awe… 9.2K stars. 1.2K forks. MIT License. 100% Opensource.

So San Francisco. An @openclaw run vending machine. Met @cvander who built it. At @frontiertower which is a high rise in San Francisco stuffed with startups.

We are completely humbled by the amazing response to our launch last week! 🫶 Now, we want to help you get the absolute best results from Stitch. In this new video, David East walks you through how to consistently get premium results. We also launched a new prompt enhancer (located under ‘+’ menu) to help you quickly collaborate on your vision before you submit your first prompt. Stitch doesn't replace the design process—it is a tool for fast exploration and refinement, which is most effective when you step into the role of Creative Director. Here are David's top strategies for taking your designs from generic to amazing: 🧠 Start with Intent: Define exactly who the design is for and how you want them to feel before you start building. 🎨 Enhance your prompt: You can use the new prompt enhancer (under the ‘+’ button’) to teach you design language and swap abstract words like "sporty" for tangible aesthetic descriptions like "high-end stationery" or "architectural limestone". 📐 Master Color Hierarchy: Treat colors as visual weight—Neutral for the canvas, Primary for ink, and Tertiary for your loudest accents. Watch the full breakdown and see the transformation here👇images in 🧵

Es importante saber cómo correr modelos locales como una alternativa a los costes de los tokens, tener una alternativa local va a ser indispensable en un futuro próximo, y es momento de que experimentes que modelos van mejor con la capacidad de tu equipo: youtube.com/watch?v=e0fulC…

Introducing OpenAgents Workspace. One workspace where all your AI agents work together, shared chat, shared files, shared browsers. Connect OpenClaw, Claude Code, Codex and more. Watch them collaborate, and work while you sleep. Open source on GitHub. Please give us a star: github.com/openagents-org… #OpenSource #AIAgents #MultiAgent

Todo el mundo sabe que Claude Code es terrible diseñando interfaces. Es por eso que han creado un MCP que le da su propia herramienta de diseño y elimina por completo el ir saltando entre Figma y tu editor. Ahora genera interfaces completas directamente en tu código, entendiendo tu sistema de diseño y adaptándose a lo que ya tienes sin romper nada. Se acabaron los diseños genéricos y las mismas UI de siempre. En el vídeo puedes ver el salto de calidad que consigue 👇

As part of the Gemma 4 release, we're launching Agent Skills: an Android app experience where you can import different skills and have Gemma 4 E2B reason and use the skills! Running entirely in the phone, available in the Google PlayStore. Try it now!

La carrera por la conectividad ya empezó… y México quiere jugar en las grandes ligas C3ntro Telecom apuesta fuerte con una inversión de 5,000 mdp para desplegar 2,500 km de fibra óptica entre Querétaro y Arizona, como parte del proyecto Tikva. El objetivo: responder al boom de la Inteligencia Artificial y el crecimiento acelerado de los Data Centers. Con gigantes tecnológicos como Google, Amazon, Meta y Microsoft impulsando la demanda, se espera que en los próximos años el tráfico de datos se dispare… y México no puede quedarse atrás. El proyecto no solo fortalecerá la infraestructura digital del país, también conectará comunidades, beneficiará a más de 27 millones de personas y aprovechará el nearshoring para posicionar a México como un hub clave en el mapa global de conectividad. ¿Qué te parece? #ExpansiónEmpresas expansion.mx/empresas/2026/…

Today, we’re launching Gemma 4, our most intelligent open models to date. Built with the same breakthrough technology as Gemini 3, Gemma 4 brings advanced reasoning to your personal hardware and devices. Here’s what Gemma 4 unlocks for developers: — Intelligence-per-parameter: Our 31B (Dense) and 26B (MoE) models deliver state-of-the-art performance for their size, outcompeting models 20x their size on @arena — Commercial flexibility: Released under a permissive Apache 2.0 license for complete developer flexibility and digital sovereignty — Agentic workflows: Native support for function-calling and structured JSON output allows you to build reliable, autonomous agents — Multimodal edge AI: The E2B and E4B models bring native vision, audio, and low latency to mobile and IoT devices — Long-context reasoning: Up to 256K context windows allow you to process entire repositories or large documents in a single prompt Whether you're building global applications in 140+ languages or local-first AI code assistants, Gemma 4 is built to be your foundation. Explore in @GoogleAIStudio or download the weights on @HuggingFace, @Kaggle, and @Ollama.

（1/8）🚀 Introducing Qwen3.6-Plus: Towards Real-World Agents! 🤖 Today, we’re thrilled to drop a major milestone in our journey toward native multimodal agents. Here is what makes Qwen3.6-Plus a game-changer： 💻 Next-level Agentic Coding: Smarter, faster execution. 👁️ Enhanced Multimodal Vision: Sharper perception & reasoning. 🏆 Top-tier Performance: Maintaining leading general capabilities. 📚 1M Context Window: Available by default via our API. Built on your invaluable feedback from the Qwen3.5 era, we’re laying a rock-solid foundation for real-world devs. Get ready to experience truly transformative ✨ Vibe Coding ✨. Huge thanks to our community! Go try it out and show us what you can build. 👇 Chat: chat.qwen.ai API: modelstudio.console.alibabacloud.com/ap-southeast-1… Blog: qwen.ai/blog?id=qwen3.6 🔔Noted：More Qwen3.6 models to come and be open-sourced! Stay tuned~ 👀#Qwen #AI #AgenticCoding #VibeCoding #Agents

Meet Gemma 4: our new family of open models you can run on your own hardware. Built for advanced reasoning and agentic workflows, we’re releasing them under an Apache 2.0 license. Here’s what’s new 🧵

🚀 EdgeClaw 2.0 is HERE — Bringing the full power of Claude Code straight into OpenClaw! 🚀 We’re beyond excited to drop this: EdgeClaw 2.0 just injected Claude Code’s smartest memory capabilities into the open-source world — in record time ⚡. We didn’t just copy memory mechanisms. We integrated #ClaudeCode into #OpenClaw, then rebuilt and supercharged it with native enhancements for truly adaptive, structured memory 🧠✨. What’s new in practice: 📂 Cross-Session Project Knowledge Retention 💡 Continuous User Preference Accumulation 🏗️ Multi-Layered Structured Memory Compared to previous setups, this represents a clear shift in how memory is handled across systems 🔄. This is an early step in a broader roadmap. The pace of iteration across the ecosystem has been accelerating, and we’re continuing to push forward with more integrations and improvements. 👉 Explore EdgeClaw 2.0: github.com/OpenBMB/EdgeCl… #OpenSource #LLMs #EdgeClaw #OpenClaw #ClaudeCode

Vuelven los Hackathones de Google a México y esta vez el equipo de Core es quien pone los retos. Iniciamos virtualmente el sábado 18 de abril. Y cerraremos con un evento final. Plus: Hay swag y premios.✨Regístrate en: rsvp.withgoogle.com/events/google-….

Algo está pasando en Villahermosa. 🧵👇 Ayer organizamos el primer Café Cursor y pasó lo que muchos creían imposible: la comunidad tech salió de sus casas para conectar, debatir y crear. No solo queremos aprender; queremos que Tabasco sea referente. (Abro hilo con fotos 📸)

We forked the leaked Claude Code source and made it work with ANY LLM: GPT, DeepSeek, Gemini, Llama, MiniMax. Open source. The name is OpenCode

Ollama is now updated to run the fastest on Apple silicon, powered by MLX, Apple's machine learning framework. This change unlocks much faster performance to accelerate demanding work on macOS: - Personal assistants like OpenClaw - Coding agents like Claude Code, OpenCode, or Codex

Esto apenas empieza. Si quieres ser parte de la próxima edición del Café Cursor Villahermosa, deja un comentario o etiqueta a ese dev que tiene que estar ahí. 🌎🚀 #ComunidadTech #Developers #Tabasco

Debates sobre IA, desarrollo y proyectos locales que demuestran que el talento no tiene código postal. El "vamos a hacerlo aquí" se sintió más fuerte que nunca. 🔥