Extism

Why not one more before we ring in the new year: mcp.run tools run natively on #Android! Dylibso Staff Research Engineer Edoardo Vacchi demonstrates how #WebAssembly brings AI tools directly to your mobile device, and integrate with Google's Gemini models. Keep your data local, and your AI personal. ???? See it in action: https://lnkd.in/gjHMPJhY

Why not one more before we ring in the new year: mcp.run tools run natively on #Android! Dylibso Staff Research Engineer Edoardo Vacchi demonstrates how #WebAssembly brings AI tools directly to your mobile device, and integrate with Google's Gemini models. Keep your data local, and your AI personal. ???? See it in action: https://lnkd.in/gjHMPJhY

It's only been a handful of days since Anthropic announced the Model Context Protocol (#MCP), which introduces a new standard to integrate software tools and data systems into AI applications. For example, giving Claude Desktop the ability to open GitHub pull requests or collaborate with your team in Notion... I see a promising future for MCP, so much that we're shipping a whole product to help see it grow! ?? Read all about it here: https://lnkd.in/gg7X29NM (of course it's built with #WebAssembly, on top of our XTP Platform!)

My #opensource history has a lot connection to where the water spins in the other direction, and #golang. Chris Mazur dared to host my first talk on #webassembly a couple years ago, in Wellington. This was on #wazero.. pure go runtime (against the odds in a rust ecosystem). This year, Katie Fry dares to host my first talk on #genai in go (against the odds in a python ecosystem), in Sydney. To write a first talk for me is a mammoth task. I get really nervous and do tons of research, ask my friends, look at a million demos. I have 300 browser tabs, tons of example code locally, several rambling text editor windows. Co-located with an Elastic meetup, my presentation at Katie's is all about Go, and I feel good about it. I had a quite decent plan together, even if later versions go farther. Yesterday, I had some initial scratches towards a real outline. This morning, Philippe Charrière pointed me to his 3 month old baby, https://lnkd.in/eTCRpNPr. This is one of his finest works: it is another improvement on his developer empathetic approach to #opensource. His examples are simple, tiered and top-notch. As GenAI is such a vast and drifty space, this is even more important for noobs. Of course, I was unsurprised this integrates with #webassembly functions via Extism. So, when you ask a question in a way the LLM understands a tool is relevant, those functions can be in any language, not just #tinygo, but anything that works in wasm, like rust. I chuckled stumbling on this, unsurprised as I worked with Phillipe earlier with his capsule FaaS project. TL;DR; I basically threw out my examples and will start over and use parakeet. This doesn't imply you will end with parakeet, but frankly there are far worse ways to start in Go. Who knows where you will end, but starting is the most important part. I'm hoping folks in Sydney enjoy this as much as I do, and also hope this turns into another successful way to relate a new tech, yet again starting where the water spins in the other direction. https://lnkd.in/ebZfF9Va

Stoked to chat with Begin.com co-founder Brian LeRoux about the company, their awesome dev tools, and an exciting new web framework that brings SSR JavaScript + Web Components to other languages like Ruby, PHP, Go, Elixir, Rust, Java, Python & more... Join us next week, August 15th at 10a Pacific! ?? https://lnkd.in/gN3EQrF4

Join Dylibso co-founders Steve Manuel & Benjamin Eckel for a sneak peek of our new solution to help you safely and securely run customer code ?? within your SaaS platform. If you want more extensibility than what webhooks and APIs can provide, XTP is the perfect fit! Details here:

Tune into the Dylibso Insiders stream! What's up with Java and WebAssembly? Join us for a deep dive into Chicory, a JVM native WebAssembly runtime! We will discuss the project, do a demo, and talk about future plans.

Huge congrats to the Dylibso team and our incredible Extism community on reaching this milestone. Our Rust SDK (just one of over a dozen) recently reached 100,000 installs... ?? That's a lot of #rust applications running WebAssembly plugins! #SeeYouAtOneMillion

?? Wanna share an exciting topic to explore the convergence of WebAssembly (WASM), Large Language Models (LLMs), and Extism - the universal plug-in system for software innovation with WASM foundations! ???? By combining the speed and efficiency of WASM with the intelligence of LLMs within the Extism framework, it may be possible to reach high standards in speed that never happened before. You may ask why, here is my reasoning behind it: In an age where performance and scalability are critical, WASM emerges as a game changer, allowing "builders" (I prefer not to use "developers" as we're not developing anymore in the typical sense) to run high-performance, low-level code directly in the browser or at any machine, release new possibilities for web or any type of applications. One of the most promising fields where WASM and LLMs can overlap is in the realm of Natural Language Processing (NLP), where WASM's speed complements LLMs' advanced linguistic capabilities, creating the way for transformative AI-driven solutions. Here is the point where Extism jumps in... Even with 3 (three) use cases... Why merge WASM and LLMs with Extism? ?? 1?? Dynamic AI-Powered Storytelling: Picture a future where Extism seamlessly integrates a WASM-driven LLM plug-in into interactive storytelling platforms. As users navigate through interesting narratives, AI dynamically crafts personalized plot twists, character dialogues, and even alternate endings based on real-time analysis of user behavior and preferences, blurring the lines between fiction and reality. Just remember pocket-sized horror / adventure novels we read during our childhood. 2?? Universal Language Decoding: Imagine a world where Extism-powered apps effortlessly translate languages in real-time, not only converting text but also seamlessly adapting spoken language and cultural nuances, and even as a sign language visually. WASM's speed combined with LLMs' linguistic mastery may enable real-time communication across borders, fostering global collaboration and understanding in ways never thought possible. 3?? AI-Driven Autonomous Development: Envision an ecosystem where Extism acts as the central nervous system for AI-driven software development platforms. WASM-LLM plug-ins analyze vast repositories of code, autonomously identifying patterns, generating optimized solutions, and even predicting future software requirements. Developers become orchestrators of AI-powered innovation, ushering in an era of self-evolving software that continuously adapts and improves. I would like to curate a github repo for demonstrating what I have on my mind but as it is not ready, I may leave here a really interesting article of how Dylibso achieves with Extism with a link to its live demo! For more info, go dive into #Extism blog post here: https://lnkd.in/dPu7rXyy Live Demo: https://lnkd.in/dwvhhzsC #WebAssembly #WASM #LLMs #FutureTech