AI Agent Toolset / Generative Media CLI
3.0k 2026-04-18
SamurAIGPT/Generative-Media-Skills
A multimodal toolset enabling AI agents to generate, edit, and display professional-grade images, videos, and audio using a CLI-powered architecture.
Core Features
Agent-Native Design with structured JSON outputs and filtering.
Access to 100+ AI models including Midjourney v7, Kling 3.0, Veo3.
Expert knowledge layer for cinematography, design, and branding.
Direct media display and local file upload support.
MCP Server for seamless integration with Claude Desktop, Cursor, etc.
Quick Start
npm install -g muapi-cliDetailed Introduction
This project provides a comprehensive, schema-driven architecture for AI agents to interact with generative media APIs. It simplifies the creation, editing, and display of high-quality images, videos, and audio through a powerful CLI, abstracting away complex API interactions. Designed for seamless integration with agents like Claude Code and Cursor, it offers an expert knowledge layer to infuse professional creative intent, making advanced multimodal generation accessible and efficient for automated workflows.