Neuron AI is a PHP framework for building AI applications in which agents connect language models, tools, data loaders, vector databases, memory, and user interfaces. PHP developers use it to create and manage applications with agent workflows, multi-agent coordination, streaming, monitoring, and human involvement.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add neuron-core/neuron-ai --skill neuron-laravel-integrationgit clone --depth 1 https://github.com/neuron-core/neuron-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/neuron-core/neuron-ai/neuron-laravel-integration)<a href="https://agentmods.dev/skills/neuron-core/neuron-ai/neuron-laravel-integration"><img src="https://agentmods.dev/badge/skills/neuron-core/neuron-ai/neuron-laravel-integration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/neuron-core/neuron-ai/neuron-laravel-integration"><img src="https://agentmods.dev/badge/skills/neuron-core/neuron-ai/neuron-laravel-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00236 | $0.14581 |
| Opus 5.5 | $0.00094 | $0.05832 |
| Sonnet 5.5 | $0.00047 | $0.02916 |
| Haiku 4.5 | $0.00024 | $0.01458 |
Grade A, and why
neuron-laravel-integration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 747 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neuron AI Laravel Integration
This skill wires Neuron agents into a Laravel 13 application: the foundations every feature stands on (classes, keys, tables, container, error mapping, the evaluation command), then the agent, the controllers that answer in JSON or stream to the browser, the queue jobs, the Stop button, observability, evaluations and tests. Neuron semantics (protocols, approvals, durability, channels, assertions) belong to the linked skills; this one owns everything Laravel-shaped. Every snippet below ran in a Laravel 13.34 application: its feature suite passes on SQLite, MySQL 8.4, MariaDB 11.7 and PostgreSQL 17, and the streaming, queue, Reverb, Redis and forked evaluation paths ran against real servers.
The Mental Model
The container builds the agent; the request binds it. An agent is resolved from the container for each request or job, then ->for($threadId) returns a copy bound to one conversation. Per-request settings (stream adapter, channel, browser tools) go on that copy. The stores are shared services in the container; the provider, tools and instructions are built by the agent's hooks for every execution segment.
| Piece | Where | Lifetime |
|---|---|---|
MessageStoreInterface → EloquentMessageStore |
NeuronServiceProvider |
singleton: holds a model class and resolves its connection on every call |
PersistenceInterface → DatabasePersistence |
NeuronServiceProvider |
bind: keeps the PDO it was given, so every resolution takes Laravel's current one |
WorkflowEngine |
autowired, no binding | per resolution: reads runs without building an agent |
SupportAgent |
app/Neuron/Agents |
transient: resolved per request or job, then bound with for() |
| Provider, tools, instructions | the agent's hooks | built again for every execution segment |
| Stream adapter, channel, browser tools | the for() copy |
one request; adapter and channel factories run once per segment |
| Thread ID | minted by the server, checked by a FormRequest | the conversation |
| Run ID of a queued turn | minted by the controller (a continuation reuses the suspended run's), serialized with the job | every delivery of that job |
| Evaluators | app/Neuron/Evaluators, built by neuron:evaluate through the container |
one command run; with --concurrency each item runs in a forked child |
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago Changed 4a8c83764f39
- 11d ago Changed · +5 lines · +12 tokens per session cd932f5d06a4
- 12d ago Changed · +5 lines 0693fa2672cd
- 15d ago First seen · 737 lines · 224 tokens per session scan A a26fee725775
neuron-laravel-integration is a skill published in the GitHub repository neuron-core/neuron-ai (2,140 stars, last pushed yesterday), licensed MIT. It adds 236 tokens to every session and 14,581 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-01.
Other skills, from other repositories
agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer.
agent-quorum-manager
Agent skill for quorum-manager - invoke with $agent-quorum-manager.
agent-dev-backend-api
Agent skill for dev-backend-api - invoke with $agent-dev-backend-api.
agent-docs-api-openapi
Agent skill for docs-api-openapi - invoke with $agent-docs-api-openapi.
agent-gossip-coordinator
Agent skill for gossip-coordinator - invoke with $agent-gossip-coordinator.
agent-raft-manager
Agent skill for raft-manager - invoke with $agent-raft-manager.