Neuron Ai Laravel Package

Agents

This repository contains Neuron AI, a PHP framework for building agentic applications.

claude-code

cursor

neuron-agent

Create, configure, and extend Neuron AI agents in PHP using providers, tools, chat history, memory, and custom workflow nodes. Use for Neuron Agent implementation, configuration, conversation lifecycle, and input/output extensions.

claude-code

neuron-evaluation

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving evaluator discovery, output configuration, result analysis, building custom assertions, multi-turn conversation evaluation, agent trajectory testing, tool-call assertions, human-in-the-loop (approval flow) testing, or simulated user conversations.

claude-code

neuron-frontend-integration

Connect a Neuron AI agent to a real frontend that executes tools in the browser — declaring deferred (frontend) tools, building the endpoint that serves a new turn or continues a suspended run, translating tool results and approval decisions coming from the Vercel AI SDK (useChat), the official AG-UI client, or CopilotKit (useFrontendTool, useInterrupt, runtime bridge), and handling partial results, retries, reloads, restarts and errors. Use this skill whenever the user mentions frontend tools, client-side tools, browser tools, DeferredTool, tool results from the frontend, AG-UI, CopilotKit, Vercel AI SDK, useChat, addToolOutput, addToolApprovalResponse, sendAutomaticallyWhen, useFrontendTool, useInterrupt, HttpAgent, AGUIInputTranslator, VercelAIInputTranslator, submitToolResults, submitApprovalDecisions, submitInputs with a frontend payload, or asks which versions of these libraries Neuron supports.

claude-code

neuron-laravel-integration

Integrate Neuron AI agents into a Laravel 13 app the framework-native way — setup checklist (App\Neuron layout, config/services.php keys, one migration, NeuronServiceProvider, bootstrap/app.php exception mapping, neuron:evaluate), container-built agents bound per thread with for(), thread authorization, JSON and AG-UI, CopilotKit or Vercel streaming, conversation reload, queued jobs through Reverb, a Mercure hub or a Redis SSE relay, failed-turn recovery, a Stop button, evaluations and tests. Use this skill whenever the user mentions Neuron AI in a Laravel app, an AI chat or assistant in a Laravel project, streaming an agent from a controller, CopilotKit or useChat with a Laravel backend, an agent in a queue job, Reverb, Mercure, reloading a conversation, stopping a generation, or testing or evaluating a Laravel agent. Also trigger for NeuronServiceProvider, EloquentMessageStore, DatabasePersistence, RunInFlightException, retry_after, RedisChannelReader, MercureChannel, StoppableHttpClient, FakeAIProvider, or config:cache and API keys.

claude-code

neuron-monitoring

Monitor Neuron AI agents and workflows with events observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, or needs to understand why an agent is behaving a certain way. Also trigger for tasks involving agent execution timeline, tool call inspection, latency problems, or general troubleshooting of Neuron AI applications.

claude-code

neuron-rag

Implement RAG (Retrieval-Augmented Generation) with Neuron AI including vector stores, embeddings providers, document loaders, retrieval strategies, and metadata filtering. Use this skill whenever the user mentions RAG, retrieval, vector search, document retrieval, semantic search, knowledge bases, chat with documents, or wants to build AI systems that can query and understand external documents. Also trigger for tasks involving vector databases, embeddings, document chunking, document schemas and metadata validation (DocumentSchema), ingestion and reindexing, retrieval strategies, or filtering retrieval by metadata (tenant scoping, source scoping, date ranges).

claude-code

neuron-streaming

Stream Neuron AI agent and workflow output to a consumer — iterating native chunks, yielding portable progress events from nodes, attaching a stream adapter for a UI protocol (Vercel AI SDK, AG-UI, SSE) or for Neuron's native vocabulary, and pushing output through a streaming channel when the consumer is not the HTTP response (queue worker, websocket, resumed run). Use this skill whenever the user mentions streaming, stream chunks, TextChunk, real-time responses, SSE, server-sent events, useChat, Vercel AI SDK, AG-UI, CopilotKit, stream adapters, streaming channels, pushing output to a websocket, Redis, Pusher or a Mercure hub, progress events from a workflow node, or testing streamed output. Also trigger for any task involving setStreamAdapter, setChannel, StreamAdapterInterface, NativeAdapter, StreamingChannelInterface, AbstractChannel, CallbackChannel, RedisChannel, PusherChannel, MercureChannel, FakeChannel, ProtocolEvent, SSEEncoder, ActivityStreamEvent, StepStartedStreamEvent, or CustomStreamEvent.

claude-code

neuron-structured-output

Design and implement structured output classes for Neuron AI agents using SchemaProperty attributes and validation rules. Use this skill when the user mentions structured output, JSON schema extraction, data validation, output classes, DTOs for AI responses, extracting structured data from LLM, or configuring property schemas. Also trigger for any task involving SchemaProperty attribute, validation rules like NotBlank/Email/Url, nested objects, arrays of objects, enums, polymorphic types with anyOf, or the Validator class.

claude-code

neuron-symfony-integration

Integrate Neuron AI agents into a Symfony 8 app, from packages, env keys, a Doctrine migration for the Neuron tables and services.yaml wiring to a shared agent bound per request with for(), a thread voter, JSON and AG-UI (CopilotKit) or useChat streaming with StreamedResponse, reload with pending approvals, Messenger background runs relayed over Redis or Mercure, a Stop button, observability, bin/console neuron:evaluate and WebTestCase tests. Use this skill whenever the user mentions Symfony together with Neuron, an AI assistant or chat in a Symfony app, streaming an agent from a Symfony controller, running an agent in Messenger or a worker, showing a conversation after a reload, a stop-generating button, or evaluating or testing agents in Symfony. Also trigger for SQLMessageStore or DatabasePersistence in services.yaml, AutowireServiceClosure, AsMessageHandler with ExecutionRequest::start, WorkerMessageFailedEvent, RedisChannelReader, MercureChannel, StoppableHttpClient, or KernelBrowser disableReboot.

claude-code

neuron-test

Write tests for Neuron AI agents, RAG systems, workflows, and tools using the built-in testing utilities. Use this skill when the user mentions testing agents, writing unit tests, mocking AI providers, testing tool execution, verifying RAG retrieval, testing workflow behavior, or creating test cases for Neuron AI components. Also trigger for any task involving PHPUnit tests, fake providers, test assertions, or quality assurance in Neuron AI projects.

claude-code

neuron-tool

Create custom tools, toolkits, and MCP integrations for Neuron AI agents. Use this skill when the user mentions creating tools, building toolkits, extending Tool class, defining tool properties, implementing tool execution, MCP server integration, Model Context Protocol, connecting external tools, multimodal tool results, or tool guidelines. Also trigger for any task involving ToolOutput, ToolProperty, ArrayProperty, ObjectProperty, AbstractToolkit, McpConnector, or StdioTransport/SseHttpTransport/StreamableHttpTransport.

claude-code

neuron-tool-approval

Implement human-in-the-loop tool approval flows with Neuron AI agents — gating risky tools behind approve/deny decisions, rendering approval UIs from chat history, submitting decisions, and building a single endpoint that handles both conversation turns and approval continuations. Use this skill whenever the user mentions tool approval, human in the loop (HITL), approve/deny actions, pending approvals, confirming dangerous tool calls, resuming a suspended agent, or building the UI side of an approval workflow.

claude-code

neuron-workflow

Build or modify Neuron AI Workflow graphs, including nodes, events, middleware, persistence, parallel branches, streaming, and human-in-the-loop interruption. Use for tasks specifically involving Neuron's Workflow APIs or custom Neuron agentic orchestration; do not trigger for generic workflow or event-driven design questions.

claude-code