its gonna be so 'great' when all AI sessions have to be linked to digital gov ID, and tracked relentlessly...

php devs, we no longer need to duct-tape python scripts just to parse a pdf 😭 launching Parsel: a fast memory efficient local document parser for PHP. pdfs, office docs & images → text, structured data, bboxes, screenshots. built for AI/RAG, NLP, invoices, search, and messy docs. composer require shipfastlabs/parsel

Finally, created an official Prettier plugin for Edge. It was overdue for a very long time. - Bump `@adonisjs/prettier-config` - Run `npm run format`

RAG vs Embeddings vs Vector Databases 𝗘𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀 turn data into numbers that capture meaning. Similar ideas end up close together, which makes semantic search possible. 𝗩𝗲𝗰𝘁𝗼𝗿 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲𝘀 store and search embeddings. They help systems find information by meaning, not just exact keywords. 𝗥𝗔𝗚 uses retrieval to improve generation. It finds relevant context, adds it to the prompt, and helps the model answer with external knowledge. Each one solves different parts of the same problem: helping AI systems use external knowledge. ↳ Without embeddings, the system cannot compare meaning. ↳ Without a vector database, retrieval becomes hard to scale. ↳ Without RAG, retrieval is not integrated into the model’s response. These same concepts are key foundational building blocks for memory-aware AI agents. If you're learning agent memory, here's a great breakdown → lucode.co/agent-memory-artic… And if you want to go deeper into unified memory systems for agents, here's a more advanced deep dive → lucode.co/unified-memory-cor… What else would you add? —— ♻️ Repost to help others learn and grow. 🙏 Thanks to @OracleDevs for sponsoring this post. ➕ Follow me ( Nikki Siapno ) to improve at AI engineering.

Top 8 Redis Use Cases. Redis is often introduced as a cache, but real systems use it for much more than speeding up database reads. That same need for fast, real-time data access is also why Redis is expanding further into AI infrastructure with Redis Iris, a context engine for AI agents that acts as a context and memory retrieval system. Learn more here → lucode.co/redis-iris-z17xd 1) 𝗖𝗮𝗰𝗵𝗶𝗻𝗴 ↳ Store hot data close to the application to reduce database load and latency. 2) 𝗦𝗲𝘀𝘀𝗶𝗼𝗻𝘀 ↳ Keep per-user or per-agent state in Redis so application servers can remain stateless. 3) 𝗥𝗮𝘁𝗲 𝗹𝗶𝗺𝗶𝘁𝗶𝗻𝗴 ↳ Track request counts across distributed services, API calls, tool usage, and model calls. 4) 𝗟𝗲𝗮𝗱𝗲𝗿𝗯𝗼𝗮𝗿𝗱𝘀 ↳ Use sorted sets to maintain live rankings without recomputing results. 5) 𝗩𝗲𝗰𝘁𝗼𝗿 𝘀𝗲𝗮𝗿𝗰𝗵 & 𝘀𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗰𝗮𝗰𝗵𝗶𝗻𝗴 ↳ Store embeddings, retrieve semantically similar data, and reuse responses across similar AI queries. 6) 𝗤𝘂𝗲𝘂𝗲𝘀 & 𝗦𝘁𝗿𝗲𝗮𝗺𝘀 ↳ Queue work, process events asynchronously, coordinate agent tasks, and track consumer progress. 7) 𝗣𝘂𝗯/𝗦𝘂𝗯 ↳ Fan out real-time messages when durability and replay aren’t required. 8) 𝗗𝗶𝘀𝘁𝗿𝗶𝗯𝘂𝘁𝗲𝗱 𝗹𝗼𝗰𝗸𝘀 ↳ Prevent multiple workers or agents from modifying the same resource at the same time. Redis has quietly evolved from “just a cache” into infrastructure for real-time coordination, retrieval, streaming, memory, and increasingly AI workloads. That evolution is reflected in their new context engine launch, focused on delivering live, agent-ready context for AI systems operating across fragmented data sources. Explore it here → lucode.co/redis-iris-z18xd What else would you add? —— ♻️ Repost to help others learn and grow. 🙏 Thanks to @Redisinc for sponsoring this post. ➕ Follow me ( Nikki Siapno ) turn on notifications.

This looks peng! Much less excited for copilot app now

Introducing Flow - The AI harness for AdonisJS 🙅 No more hallucinated APIs. 🙅 No more code that drifts from conventions that becomes painful to maintain. Because AdonisJS is opinionated, we can ground agents into actually following the framework, not guessing at it. plus.adonisjs.com/flow Thread below 👇

Stop lying to yourself. AI isn't going to replace software engineers. It's just going to turn all of us into full-time code reviewers for the worst, most confident junior developer imaginable.

Your AI agent can only move as fast as what it can understand. This is why @enunomaduro built Laravel PAO (PHP agent-optimized output). PAO gives PHPUnit, Pest, PHPStan, and Rector output as structured JSON so agents know exactly where to look. Already building with Laravel? Install it with composer require 𝚕𝚊𝚛𝚊𝚟𝚎𝚕/𝚙𝚊𝚘 --𝚍𝚎𝚟. New Laravel apps include it by default. laravel.com/blog/introducing…

How often do you use `shouldRun` on migrations? A very useful feature for controlling when you want certain migrations to be run or skipped.

Now that I built the official Jetbrains plugin for Adonisjs/Edgejs, might build a Jetbrains plugin for @statamic Antlers. I much prefer blade with Statamic, but reindeers need love too!

Passkeys are now NATIVELY supported in Laravel 🤩 This is why I love Laravel SO MUCH 💯

I really just like to program Hands on keyboard, music, deeply thinking and enjoying the process

Tell us something we don't know lol LLMs Corrupt Your Documents When You Delegate arxiv.org/html/2604.15597v1

Just published a public roadmap for AdonisJS and here are some of the bigger items on the list. 👉 OpenAPI schema generation 👉 An agent-grade CLI with introspection 👉 MCP servers support 👉 A dedicated command to run codegen on-demand Comment or upvote to help me prioritize what to build first. Also, a quick reminder 👇 If you or your company depends on AdonisJS, the Insiders program is right there too. Early access to new releases, and it's what keeps me working full-time on the framework. adonisjs.com/roadmap

Someone open-sourced an Android emulator that runs in Docker. It's called docker-android. One docker command spins up a complete Android device with ADB port-forwarding, KVM, and GPU acceleration.. fully headless and CI-ready. 100% Open Source.

Reminder for Laravel developers 🫡

We use Linux, and Windows, and Mac. People are very disingenuous about OSs

Today's Laravel release includes debounced queued jobs. ✋ Use #[DebounceFor(seconds)] on a job to get last-dispatch-wins behavior, so noisy repeat dispatches collapse into one execution. Includes max wait support, custom cache store via debounceVia(), and a JobDebounced event for superseded jobs. laravel.com/docs/13.x/queues…

OpenCode ❤️ WSL or something?