Tracks the tokens and cost of every laravel/ai call, with a filterable Livewire dashboard, budgets and a synced AI model price list.

Stop AI coding agents from faking "done" in Laravel. ai:verify runs only the tests, Larastan, Pint and Laravel checks a diff needs, fails on deleted or skipped tests, and stamps verified commits for CI. ai:graph gives agents a code graph of routes, controllers, models, views and tests, with impact analysis.

OpenTelemetry exports for the Laravel AI SDK with pluggable observability adapters.

Self-hosted metering + budget enforcement for AI/LLM & agent calls in Laravel. Traces, token/cost attribution, a built-in dashboard, and multi-scope spend limits — with no external service.

A stateless MCP (Model Context Protocol) server for Laravel with ready-made blog tools: let Claude list, draft, edit, schedule and publish your posts.

Seed Eloquent models with realistic data generated by an LLM (OpenAI or any OpenAI-compatible server)

Guarded tools and assurance tests for Laravel AI agents: workspace isolation, honest failures and evidence on every tool call.

An MCP (Model Context Protocol) server for the Credo payment gateway, powered by zowesoft/laravel-credo.

Expose Laravel AI SDK tools in Blade through browser-native WebMCP.

A reusable Laravel package for AI-powered content summarization supporting OpenAI, Anthropic, Gemini, Mistral, Groq, and OpenRouter.

Expose laravel/mcp tools and resources as WebMCP tools (document.modelContext) in the browser.

The all-in-one, AI-powered Laravel admin panel. Beautiful light and dark UI, fluent CRUD, RBAC, widgets, media, audit logs and a headless API, installed in under 3 minutes.

A Laravel agent harness with swappable loops. Pick how your AI agent thinks, switch with one line, compare which works best.

One Action class for every surface of a Laravel app: web and JSON routes, the CLI, queued jobs, laravel/ai agents, MCP clients and typed TypeScript.

A BotMan-powered, tool-calling AI chat widget for Laravel with a swappable AI driver (Gemini by default).

Securely expose Laravel Pulse production monitoring data to AI agents through an OAuth-protected MCP server.

AI agent skills and guidelines for Laravel — auto-discovered by Laravel Boost and synced to Claude Code, Cursor, GitHub Copilot, Codex and Junie. Includes Backpack for Laravel v6 and HyperPay (OPPWA).

Make your laravel/mcp servers discoverable by AI agents: server cards, llms.txt, robots.txt, Link headers and a bot gate.

A drop-in landing page and AI chatbot UI for Laravel applications.

Self-healing Laravel apps: turns a production exception into a proven, reviewed pull request with a failing test, a minimal patch and red-to-green evidence.

Laravel Pulse cards and recorders for x-laravel/embedding.

MariaDB 11.7 native vector similarity driver for x-laravel/embedding.

MySQL 9 native VECTOR similarity driver for x-laravel/embedding.

PostgreSQL pgvector similarity driver for x-laravel/embedding.

Qdrant vector database similarity driver for x-laravel/embedding.

SQL Server 2025 native vector similarity driver for x-laravel/embedding.

Oracle 26ai vector similarity driver for x-laravel/embedding.

Automatic vector embedding generation for Laravel Eloquent models using laravel/ai.

phpClaw adapter for Laravel. Add AI agents to any Laravel app with a single composer require.

Turn Livewire components and Laravel services into agent-ready tools with PHP 8 attributes. One definition powers your UI, LLM tool calling, and MCP endpoints.

Laya as a first-class classification provider for laravel/ai: typed choice, score and yes/no decisions from a self-hosted, multilingual System 1 model.

Laravel Boost rules, skills, and architecture tests for pragmatic, Laravel-native Domain-Driven Design.

AI agent guidelines and skills for the LaravelUi5 stack — read by Laravel Boost, so a coding agent writes laravelui5/* correctly instead of guessing.

Unofficial Laravel/PHP SDK for TypeSafe AI's System One decision model (Jev): typed choice, score and yes/no judgments, a validation rule and test fakes.

Laravel integration for adams100111/typesafe-php — config, a facade, and a transport on Laravel's HTTP client so Http::fake() works in your tests. Unofficial; not affiliated with TypeSafe.

Opt-in Laravel middleware for spam and prompt injection detection using Laravel AI and Typesafe Jev.

Laravel-native SDK for the TypeSafe (Jev / System One) API.

The layer between laravel/ai and a product: conversations, retrieval over a pluggable corpus, spend governance, and PII masking.

A Laravel client and JWT token factory for Agno AgentOS 3.

Unofficial Laravel integration for the butochnikov/typesafe-sdk-php TypeSafe Jev client.

AI Voice Agent capabilities for Laravel, built on top of easybdit/laraveleasyai (speech-to-text, text-to-speech, voice sessions, voice-enabled tool-calling agents).

Cost-governed LLM execution for Laravel: per-profile spend ceilings enforced before the call, model fallback, JSON Schema validation with one re-ask, and real cost accounting per run.

A portable Laravel content engine — blog posts with categories and tags, DB-backed CMS pages, FAQs and reusable content chunks, media-library images, Nova admin, and a built-in MCP server so AI agents can manage the whole archive remotely with an API key.

Embed a Sveda AI agent in Laravel (sessions + host MCP). https://sveda.dev/docs/hosts/laravel

Embed a Sveda AI agent in Laravel (sessions + host MCP). https://sveda.dev/docs/hosts/laravel

Vendor-neutral AI agent application runtime for Laravel with governed tools, deterministic workflows, connectors, MCP/A2A, knowledge, deployments, evals, and observability.

A component kit (turn/event data model + Livewire chat UI) for laravel/ai agents.

OpenTelemetry tracing for the Laravel AI SDK, following the OpenTelemetry GenAI semantic conventions.

PHPUnit evals for laravel/ai agents: LLM judges, tool trajectories, and scorers.

Turn any Laravel app into a secure AI agent: automatic and custom vector embedding generation, multi-provider AI switching with auto-failover (Gemini, OpenAI/ChatGPT, DeepSeek, Anthropic/Claude, or any custom LLM), zero-config controller-to-tool discovery, and PostgreSQL/MySQL/MongoDB/Qdrant/Pinecone vector database support.