What you need: PHP 8.3+ with phpredis, Composer, Node 20+, Docker (or your own MySQL 8 and Redis), an Anthropic or OpenAI key.
git clone the repo, cd into it
docker compose up -d
composer setup
add your API key to .env
php artisan db:seed
composer run dev
Log in with [email protected] / password and ask:
"Show me the headline KPIs for this month."
composer setup does the boring part (deps, .env, app key, migrations, assets). You ask, the UI builds itself.
github.com/neuron-core/gener…
Agent-written code passes the demo, good architecture or not.
Phase 2 is where you find out if your team got an architecture it can build on, or something that just works but is a mess.
The Kickstart: one session with the people who built Neuron, on your project. 👇
#PHP
Start with a short intro call. If there's a fit, your team's first session is on us.
Book it here: neuron-ai.dev/kickstart
Ask an AI agent for your KPIs and you usually get a paragraph of numbers.
In this demo the agent builds the dashboard instead: KPI cards, a revenue chart, a top products table. Live, inside a Laravel app, with the agent written in PHP. 📊
How it works: the agent reads the DB schema, runs read-only SQL, then calls render_cards, render_chart or render_table.
It picks the component, passes the data, and Vue components stream into the chat over AG-UI. Neuron v4 on Laravel 13.
It's a demo, not a BI product. The pattern is the point, and it's yours to take apart.
Clone it, run it, ask your own question:
github.com/neuron-core/gener…
#PHP #Laravel
1/ His agents never call each other. The workflow decides what runs next.
Jules Langlois built a personal "Jarvis" with small PHP agents and a Neuron workflow, then wrote up how he did it. 🧵
7/ He's upfront that it's a prototype: "this prototype was built with AI coding assistance, and it is meant as a starting point, not production code."
He tested it on Neuron 4.1 with simulated agents and in-memory adapters, failure and resume included.
8/ Read Jules's article 📖
dev.to/jouliose/building-a-j…
Would you split the roles differently? Tell us below. The code he proposed is in his PR:
github.com/neuron-core/neuro…
#PHP #AIAgents
Your agent's chat froze at 10 KB. No exception, no error in the console.
Valerio, Neuron's CTO, hit this after moving an agent into a queue worker: one tool result (the content of a file) went over Pusher's 10 KB limit, and the message was simply rejected. 🧵
Every run ends with one of three terminal events: completed, interrupted, failed. The UI knows when to stop waiting.
The chat history stays the source of truth, the stream is a convenience layer on top.
To set it up, ask your coding agent to use the /neuron-streaming skill.
The full story and how the protocol works, in Valerio's article 👇
inspector.dev/streaming-ai-a…




