Search

More Filters

Show More
Add Listing
Go Back

neuron ai

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Neuron AI is a PHP library and SDK designed to let developers create full-featured AI agents as standalone components inside PHP applications. It provides a base Agent class to extend, a SystemPrompt helper to structure prompts, built-in memory for conversational state, and support for tools, toolkits and function calls. The project also includes a RAG class for retrieval-augmented generation, structured output helpers for producing typed responses, a Workflow system to compose nodes and edges, and an MCP connector to surface external tools. It targets PHP 8.1+, is installable via composer, and includes examples showing how to create agents, attach MySQL toolkits, connect vector stores and embeddings, and enable observability for agent executions.

Links

Stars
936
App URL
https://github.com/inspector-apm/neuron-ai
Github Repository
https://github.com/inspector-apm/neuron-ai/blob/main/README.md

Categorization

App Details

Features
The repository offers an extendable Agent base class, SystemPrompt for consistent prompts, conversation memory management, and tool/toolkit integration such as a MySQLToolkit. It supports structured output via schema annotations, a RAG implementation with embeddings and vector store interfaces, and a Workflow engine with nodes, edges and human-in-the-loop support. There is an MCP connector to import tools from MCP servers. Observability is supported through Inspector integration for execution timelines. The AI provider abstraction lets you switch providers with one line of code and supported providers listed include Anthropic, OpenAI, OpenAI on Azure, Gemini, Ollama, HuggingFace, Mistral and Grok. The package requires PHP 8.1 and is installable via composer.
Use Cases
Neuron AI helps developers build production-ready, agentic features without reimplementing orchestration, prompting and integration logic. It abstracts LLM providers so teams can swap models or providers with minimal code changes. Built-in memory and structured output reduce engineering effort for chat state and typed responses for downstream systems. RAG components and embeddings/vector store interfaces simplify retrieval workflows. Toolkits and the MCP connector enable reuse of existing databases and external tools. The Workflow engine allows custom multi-step flows and human-in-the-loop checkpoints for validation. Inspector observability aids debugging and reproducibility by showing agent execution timelines and LLM calls. Overall it shortens time to integrate complex AI behaviors into PHP applications.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*