Short Video from Andrew DalPino - creator of RubixML (A high-level machine learning and deep learning library for the PHP language.
)
https://www.youtube.com/watch?v=5YtNugpMhyQ

New version 0.6 of my book "AI with PHP" is available for reading:
https://apphp.gitbook.io/artificial-intelligence-with-php

Also, you may find more online examples here:
https://aiwithphp.org/examples/

If you want to check AI agent platform with cyclic thinking, persistent memory and more...
https://github.com/rnr1721/depthnet

The most popular ML library in PHP reaches 1,000,000 downloads. Only last 24h - more than 10,000 - here we go!

PHP - Oh Really, Tensors?

Extension for PHP, that provides high performance tensor mathematics. It supports a wide range of mathematical operations on tensors, including element-wise computations, reductions, linear algebra functions, and more.

https://github.com/krakjoe/ort

Adding NER to a PHP Project: What Worked and What Didn’t
https://www.linkedin.com/in/sam-akopyan/

For Russian speaking members:
https://habr.com/ru/articles/948014/

Announcing the Official PHP SDK for MCP

The Model Context Protocol (MCP) is an open protocol introduced by Anthropic to enable AI applications to connect with and utilize external tools and data sources, akin to a standardized "USB-C port" for AI systems.

https://thephp.foundation/blog/2025/09/05/php-mcp-sdk/

My article about Neuron AI Framwork.
The original article written in Russian, here the link: https://habr.com/ru/articles/960050/
But you may also see it translated in English (just scroll down)
https://habr-com.translate.goog/ru/articles/960050/?_x_tr_sl=ru&_x_tr_tl=en&_x_tr_hl=en&_x_tr_pto=wapp

🚀 New PHP Library Release: PrettyPrint

Just published PrettyPrint, a tiny, zero-dependency PHP utility that formats arrays with clean, Python-like readability — inspired by PyTorch!

✨ Features:
• Callable pretty-printer for numeric arrays
• Aligned 2D table formatting
• 3D tensor with head/tail blocks
• Summarized tensor-style views
• Flexible output options
• Perfect for ML experiments, debugging, logging & teaching

📦 Packagist: https://packagist.org/packages/apphp/pretty-print

Give it a try and make your arrays look awesome! 🎉

https://dev.to/mark_redding_fb1c365503df/accelerating-php-development-with-cursor-ai-ln1

Mark Redding, a manager at Best Name Badges, has been exploring AI-powered development tools to streamline PHP workflows. Cursor AI has proven to be a game-changer for the team.

New Repo: Awesome PHP Machine Learning

I’ve just launched awesome-php-ml — a curated list of Machine Learning, AI, and LLM tools for PHP developers.

It covers:
- Machine Learning & Deep Learning
- LLMs, agents & AI APIs
- Math, statistics & vector search
- Tools, model serving & framework integrations (Laravel, Symfony)
- Resources & platforms
- and more

👉 https://github.com/apphp/awesome-php-ml

If you’re building AI with PHP or looking for the best libraries in the ecosystem, check it out ⭐
Contributions welcome!

If you didn't see this, now is the time to do it.
https://www.youtube.com/watch?v=w542sIZppzE

Hey everyone!
Just published a new article: AI for PHP Developers — Practical Use of TransformersPHP!
Dive into how you can bring real AI into your PHP projects without complex infrastructure, using TransformersPHP for tasks like embeddings, classification and semantic search — all right inside your code.

Read it here:
English:
https://medium.com/@leumas.a/ai-for-php-developers-practical-use-of-transformersphp-fa9a2416bafc
Feedback, thoughts, and questions are very welcome!
Russian:
https://habr.com/ru/articles/993966/

My new article "From Arrays to GPU — how the PHP ecosystem is moving toward real ML"
In Russian: https://habr.com/ru/articles/1019250/
In English: https://medium.com/@leumas.a/from-arrays-to-gpu-how-the-php-ecosystem-is-moving-toward-real-ml-3e6d661e9abe

Want to get a real feel for machine learning in practice?

Here’s a simple but powerful exercise: classify thousands of digits (0 vs 1) from the classic MNIST dataset (12,666 train samples and 2,116 test samples) using logistic regression – trained with gradient descent.
Just 5 epochs!

What you’ll get out of it:

- see how a model actually works with image data
- understand where linear models start to break down
- try a clean implementation in pure PHP (accuracy: 99.91%)
- compare it with a more production-ready approach using RubixML (accuracy: 99.95%)

If you’ve been meaning to move from theory to something hands-on, this is a great place to start:
https://aiwithphp.org/books/ai-for-php-developers/examples/part-3/logistic-regression/case-0/mnist-0-1

My new article on Habr (in Russian):
"AI for PHP Developers. Part 6: Bag of Words and TF-IDF – How a Computer Turns Text into Math"
https://habr.com/ru/articles/1034874/

Hey, there! 👋

Looking for something to read this weekend?

I've put together a small overview of the rapidly growing AI ecosystem in PHP – from simple OpenAI API integrations to modern agent frameworks, multi-agent systems, and full-fledged agent platforms.

If you've been wondering what's happening beyond basic LLM calls in the PHP world, this article covers some of the most interesting projects and trends shaping the ecosystem today.

📖 Read here in English:
https://medium.com/@leumas.a/the-ai-agent-ecosystem-in-php-from-simple-openai-calls-to-multi-agent-platforms-320a74e78d95
📖 in Russian:
https://habr.com/ru/articles/1041594/

Hey, hey, dee-dee! Enjoy!
https://www.youtube.com/watch?v=SoqAP4gSDac