Key Concepts

Learn the fundamental concepts to be sure Neuron it's the best fit for your business needs.

Neuron AI is designed to provide you with a complete toolkit to implement AI driven applications, making it easy to integrate into your existing system.

Most Neuron AI framework components do not implement active constructors, they just provide you features to implement your own agentic behavior. The two most important classes Agent and RAG, are designed to be extended to create your specific implementation. They are rarely used as standalone objects.

This ensures the portability of your agents because all the moving parts are encapsulated into a single entity that you can just run wherever you want in your application.

use NeuronAI\Agent;

class SEOAgent extends Agent
{
    public function provider(): AIProviderInterface
    {
        // return an AI provider (Anthropic, OpenAI, Mistral, etc.)
    }
    
    public function instructions(): string
    {
        return "define the system message";
    }
    
    public function tools(): array
    {
        return [
            // Tool::make()...
        ];
    }
}

Package Dependencies

We intentionally decided to build Neuron as free as possible from external dependencies. The entire framework ships with just one dependency: "guzzlehttp/guzzle": "^7.0"

Without bringing dozens of dependencies inside your application, you do not risk being locked out of Neuron if you need to upgrade your current architecture, like the web application framework (Laravel, Symfony, CodeIgniter, etc) to a newer version, or integrate new dependencies.

Based on our experience, a bad dependency chain could be a very unpleasant surprise when it is too late. You have already spent a lot of effort to implement your AI interactions, and suddenly it has become a bottleneck because the dependencies make it impossible to upgrade and evolve the rest of your system.

We want you to know that with Neuron AI it's not the case.

Extensibility

Every component of the framework depends on its own interface. This guarantees you the ability to create new concrete implementations of every component to interact with external systems and pass them to your agents with confidence.

In the components documentation you will find the dedicated section of how to implement a new one, basically extending its interface.

Do you want to implement a new Vector Store, or an Embeddings Provider? Follow the documentation and feel free to send us a PR with your new module. We will be happy to integrate them as a part of the framework to ensure first party support and maintenance.

Observability

Neuron is designed with a built-in system to make your agent and RAG implementations observable. You can start monitoring your agents activities and performance with just one line of code. Follow the dedicated section in the observability section:

Observability