BananaStudio-AI/MPC_apidog

1

stars

135

commits

Python

primary language

Nov 30, 2025

updated

README

Banana Studios Tier-1 Production Stack

Direct Provider Integration (FAL, OpenAI, Anthropic, Hugging Face)

A lean, production-ready creative automation system for generating and publishing media content. This repository contains the core Tier-1 production infrastructure for Banana Studios, focusing on direct provider API calls without proxy layers.

🎯 Mission

Generate, compose, and publish creative media assets (images, videos, audio, scripts) using Tier-1 providers only:

  • FAL AI - Image and video generation
  • OpenAI - Script and copywriting
  • Anthropic - Text generation
  • Hugging Face Inference - Voiceovers and audio

🚀 Quick Start

Prerequisites

  • Node.js 20+
  • Python 3.8+ (for tests)
  • API keys for Tier-1 providers

Setup

# Configure environment (from project root)
cp env.example .env
# Edit .env with your API keys:
# - FAL_API_KEY
# - OPENAI_API_KEY
# - ANTHROPIC_API_KEY
# - HF_API_KEY

# Install dependencies
cd mpc-api
npm install

# Start development server
npm run dev

Test Endpoints

# Test image generation
curl -X POST http://localhost:3000/api/fal/image \
  -H "Content-Type: application/json" \
  -d '{"prompt": "a cute red panda"}'

# Test video generation
curl -X POST http://localhost:3000/api/fal/video \
  -H "Content-Type: application/json" \
  -d '{"prompt": "a cute red panda animation", "duration": 3}'

📁 Repository Structure

.
├── mpc-api/               # Main API server (Express + TypeScript)
│   ├── src/
│   │   ├── providers/     # Direct provider wrappers
│   │   ├── agents/        # Agent modules (Script, Visual, Voice, Publisher)
│   │   └── routes/        # API endpoints
│   └── package.json
├── outputs/               # Generated content
│   ├── images/
│   ├── videos/
│   └── audio/
├── docs/
│   └── production/        # Tier-1 production documentation
└── tests/                 # Test scripts

🔑 Key Features

  • Direct Provider Calls - No proxy layers, maximum reliability
  • Agent-Based Architecture - Modular content generation workflows
  • Production Endpoints - Ready-to-use API routes
  • Async Video Generation - Automatic polling for long-running jobs
  • Lightweight Dependencies - Only essential packages

📚 Documentation

🧩 API Endpoints

FAL Endpoints

  • POST /api/fal/image - Generate image (synchronous)
  • POST /api/fal/video - Start video generation (async)
  • GET /api/fal/video/:requestId/status - Check video status
  • GET /api/fal/video/:requestId - Get video result
  • POST /api/fal/generate - Unified image/video generation

Production Endpoints

  • POST /api/production/content - Complete content package
  • POST /api/production/short - Short-form content generator

🔧 Development

# Navigate to API directory
cd mpc-api

# Development mode (hot reload)
npm run dev

# Build for production
npm run build

# Start production server
npm start

# Run tests (from project root)
cd ..
python test_tier1_production.py

📦 Dependencies

Only Tier-1 essential packages:

  • express - Web framework
  • typescript - Type safety
  • dotenv - Environment configuration

Provider-specific integrations use direct API calls (no SDK dependencies).

🎯 Use Cases

  • Automated YouTube Shorts generation
  • Social media content creation
  • Batch image/video generation
  • Script writing and voiceover workflows
  • Content pipeline automation

📄 License

Proprietary - Banana Studios

🆘 Support

For issues or questions, see docs/production/README.md


Version: 1.0.0-tier1
Status: Production Ready
Last Updated: November 2025

Contributors

BananaStudio-AI

128 commits

Copilot

7 commits

BananaStudio-AI/MPC_apidog

1

stars

135

commits

Python

primary language

Nov 30, 2025

updated

README

Banana Studios Tier-1 Production Stack

Direct Provider Integration (FAL, OpenAI, Anthropic, Hugging Face)

A lean, production-ready creative automation system for generating and publishing media content. This repository contains the core Tier-1 production infrastructure for Banana Studios, focusing on direct provider API calls without proxy layers.

🎯 Mission

Generate, compose, and publish creative media assets (images, videos, audio, scripts) using Tier-1 providers only:

  • FAL AI - Image and video generation
  • OpenAI - Script and copywriting
  • Anthropic - Text generation
  • Hugging Face Inference - Voiceovers and audio

🚀 Quick Start

Prerequisites

  • Node.js 20+
  • Python 3.8+ (for tests)
  • API keys for Tier-1 providers

Setup

# Configure environment (from project root)
cp env.example .env
# Edit .env with your API keys:
# - FAL_API_KEY
# - OPENAI_API_KEY
# - ANTHROPIC_API_KEY
# - HF_API_KEY

# Install dependencies
cd mpc-api
npm install

# Start development server
npm run dev

Test Endpoints

# Test image generation
curl -X POST http://localhost:3000/api/fal/image \
  -H "Content-Type: application/json" \
  -d '{"prompt": "a cute red panda"}'

# Test video generation
curl -X POST http://localhost:3000/api/fal/video \
  -H "Content-Type: application/json" \
  -d '{"prompt": "a cute red panda animation", "duration": 3}'

📁 Repository Structure

.
├── mpc-api/               # Main API server (Express + TypeScript)
│   ├── src/
│   │   ├── providers/     # Direct provider wrappers
│   │   ├── agents/        # Agent modules (Script, Visual, Voice, Publisher)
│   │   └── routes/        # API endpoints
│   └── package.json
├── outputs/               # Generated content
│   ├── images/
│   ├── videos/
│   └── audio/
├── docs/
│   └── production/        # Tier-1 production documentation
└── tests/                 # Test scripts

🔑 Key Features

  • Direct Provider Calls - No proxy layers, maximum reliability
  • Agent-Based Architecture - Modular content generation workflows
  • Production Endpoints - Ready-to-use API routes
  • Async Video Generation - Automatic polling for long-running jobs
  • Lightweight Dependencies - Only essential packages

📚 Documentation

🧩 API Endpoints

FAL Endpoints

  • POST /api/fal/image - Generate image (synchronous)
  • POST /api/fal/video - Start video generation (async)
  • GET /api/fal/video/:requestId/status - Check video status
  • GET /api/fal/video/:requestId - Get video result
  • POST /api/fal/generate - Unified image/video generation

Production Endpoints

  • POST /api/production/content - Complete content package
  • POST /api/production/short - Short-form content generator

🔧 Development

# Navigate to API directory
cd mpc-api

# Development mode (hot reload)
npm run dev

# Build for production
npm run build

# Start production server
npm start

# Run tests (from project root)
cd ..
python test_tier1_production.py

📦 Dependencies

Only Tier-1 essential packages:

  • express - Web framework
  • typescript - Type safety
  • dotenv - Environment configuration

Provider-specific integrations use direct API calls (no SDK dependencies).

🎯 Use Cases

  • Automated YouTube Shorts generation
  • Social media content creation
  • Batch image/video generation
  • Script writing and voiceover workflows
  • Content pipeline automation

📄 License

Proprietary - Banana Studios

🆘 Support

For issues or questions, see docs/production/README.md


Version: 1.0.0-tier1
Status: Production Ready
Last Updated: November 2025

Contributors

BananaStudio-AI

128 commits

Copilot

7 commits

Languages

Python

68.7%

TypeScript

20.7%

JavaScript

9.9%