---

🤔 Why CGMB?

$3 Optimally integrates Claude's reasoning power, Gemini CLI's search capabilities, and AI Studio's generation power. Ahead of the 2026 AI trend: "Specialized AI Collaboration"

$3 Complete with a single npm install. Tedious setup is automated

$3 Follows the Anthropic Model Context Protocol. Enterprise-grade reliability with 95% self-healing rate

---

✨ What's New in v1.1.0

| Feature | Description |
|---------|-------------|
| 🪟 Full Windows Support | Native support for both CLI and MCP |
| 📝 Enhanced OCR Processing | Automatic text extraction from scanned PDFs |
| 🚀 Latest Gemini Models | Support for gemini-2.5-flash, gemini-3-flash |
| 🔐 OAuth Authentication | File-based authentication compatible with Claude Code |
| 🌐 Auto Translation | Japanese to English translation for image generation |
| 📊 Smart Routing | PDF URLs to AI Studio, web pages to Gemini CLI |
| ⚡ Performance Optimization | Reduced timeouts, lazy loading, caching |
| 🛡️ Error Recovery | 95% self-healing with exponential backoff |

---

🏗️ Architecture

``mermaid
flowchart TD
A[Claude Code] --> B[CGMB]

B --> C[Gemini CLI]
B --> D[Claude Code]
B --> E[AI Studio]
`

| Layer | Specialization | Timeout |
|:-----:|:---------------|:-------:|
| 🔍 Gemini CLI | Web search, real-time information | 30s |
| 🧠 Claude Code | Complex reasoning, code analysis | 300s |
| 🎨 AI Studio | Image generation, audio synthesis, OCR | 120s |

---

🚀 Quick Start

$3

- Node.js ≥ 22.0.0
- Claude Code CLI installed
- Gemini CLI (auto-installed)

$3

`bash
npm install -g claude-gemini-multimodal-bridge
`

> 💡 The postinstall script automatically:
> - Installs Gemini CLI
> - Sets up Claude Code MCP integration
> - Creates .env template
> - Verifies system requirements

$3

Create a .env file in your working directory:

`bash
AI_STUDIO_API_KEY=your_api_key_here
`

🔗 Get API key: https://aistudio.google.com/app/apikey

$3

`bash
gemini
`

$3

`
I installed CGMB via NPM. Please check my current environment for the cgmb command and help me use it.
`

---

💡 Usage Examples

CGMB integrates seamlessly with Claude Code. Just use the "CGMB" keyword:

`bash

🎨 Image generation

"CGMB generate an image of a futuristic city"

📄 Document analysis (use absolute paths)

"CGMB analyze the document at /full/path/to/report.pdf"

🌐 URL analysis

"CGMB analyze https://example.com/document.pdf"

🔍 Web search

"CGMB search for the latest AI news"

🎵 Audio generation

"CGMB create audio saying 'Welcome to our podcast'"

📝 OCR-enabled PDF analysis

"CGMB analyze this scanned PDF document with OCR"
`

$3

1. Include "CGMB" in your Claude Code request
2. CGMB automatically routes to the optimal AI layer:
- 🔍 Gemini CLI: Web search, latest information
- 🎨 AI Studio: Images, audio, file processing
- 🧠 Claude Code: Complex reasoning, code analysis

---

🤖 Models Used

| Purpose | Model ID | Layer |
|:-------:|:---------|:-----:|
| 🔍 Web Search | gemini-3-flash | Gemini CLI |
| 🎨 Image Generation | gemini-2.5-flash-image | AI Studio |
| 🎵 Audio Generation | gemini-2.5-flash-preview-tts | AI Studio |
| 📄 Document Processing | gemini-2.5-flash | AI Studio |
| 📝 OCR/Text Extraction | gemini-2.5-flash | AI Studio |
| 🔮 General Multimodal | gemini-2.0-flash-exp | AI Studio |

---

📈 Performance

$3 Authentication Overhead Reduction

$3 Search Cache Hit Rate

$3 Automatic Error Recovery Rate

---

📄 PDF Processing & OCR

$3

- ✅ Supports both text-based and scanned PDFs
- ✅ Automatic OCR detection
- ✅ Native OCR processing via Gemini File API
- ✅ Multi-language support

$3

`
PDF Input → Upload → OCR Processing → Content Analysis → Output Results
`

$3

- Text-based PDFs
- Scanned PDFs (OCR processing)
- Image-based PDFs (OCR conversion)
- Mixed content
- Complex layouts (tables, charts, formatted content)

---

📂 File Organization

Generated content is automatically organized:

`
output/
├── images/ # 🎨 Generated images
├── audio/ # 🎵 Generated audio files
└── documents/ # 📄 Processed documents
`

Access via Claude Code:
- get_generated_file: Retrieve specific files
- list_generated_files: List all generated files
- get_file_info: Get file metadata

---

🔧 Configuration

$3

`bash

Required

AI_STUDIO_API_KEY=your_api_key_here

Optional

GEMINI_API_KEY=your_api_key_here
ENABLE_CACHING=true
CACHE_TTL=3600
LOG_LEVEL=info
`

$3

CGMB automatically configures Claude Code MCP integration:
- 📍 Config path: ~/.claude-code/mcp_servers.json
- ⚡ Direct Node.js execution
- 🔒 Safe merge without overwriting existing servers

---

🪟 Windows Environment

CGMB fully supports Windows in v1.1.0:

| Feature | Status |
|---------|:------:|
| CLI | ✅ All commands work |
| MCP Integration | ✅ MCP tool calls work correctly |
| Path Resolution | ✅ Automatically handles C:\path\to\file format |
| Gemini CLI | ✅ Full compatibility with Windows version |

`powershell

Absolute paths recommended

cgmb analyze "C:\Users\name\Documents\report.pdf"

Set environment variable (PowerShell)

$env:AI_STUDIO_API_KEY = "your_api_key_here"

Set environment variable (Command Prompt)

set AI_STUDIO_API_KEY=your_api_key_here
`

---

🐧 Linux / WSL Environment

CGMB works fully on Linux and WSL:

| Feature | Status |
|---------|:------:|
| CLI | ✅ All commands work |
| MCP Integration | ✅ MCP tool calls work correctly |
| Path Resolution | ✅ Supports /mnt/ WSL paths and Unix paths |
| Gemini CLI | ✅ Full compatibility with Linux version |

`bash

Use Unix path format

cgmb analyze /home/user/documents/report.pdf

WSL environment example

cgmb analyze /mnt/c/Users/name/Documents/report.pdf

Set environment variables

export AI_STUDIO_API_KEY="your_api_key_here"
export CGMB_CHAT_MODEL="gemini-2.5-flash"
`

---

🔍 Troubleshooting

$3

`bash
export CGMB_DEBUG=true
export LOG_LEVEL=debug
cgmb serve --debug
`

$3

If OCR results are inaccurate:
- Use high-resolution scanned PDFs (300+ DPI)
- Ensure clear, high-contrast text
- Avoid skewed or rotated documents

If large documents timeout:
- Split large PDFs before processing (limit: 50MB, 1,000 pages)
- Extend timeout: export AI_STUDIO_TIMEOUT=180000

---

💰 API Costs

CGMB uses pay-per-use APIs:
- 📊 Google AI Studio API Pricing Details

---

📁 Project Structure

`
src/
├── core/ # 🎯 Main MCP server and layer management
├── layers/ # 🔌 AI layer implementations
├── auth/ # 🔐 Authentication system
├── tools/ # 🛠️ Processing tools
├── workflows/ # 📋 Workflow implementations
├── utils/ # 🔧 Utilities and helpers
└── mcp-servers/ # 🌐 Custom MCP servers
``

---

🔗 Links

$3 - GitHub - NPM - Issues

$3 - Claude Code - Gemini CLI - Google AI Studio - MCP

$3 - Google AI Studio - Claude - Gemini API

---

📜 Version History

$3

- 🪟 Full Windows Support: Native Windows support for both CLI and MCP
- 📝 Enhanced OCR: Automatic OCR processing for image-based PDFs
- 🚀 Latest Gemini Models: Support for gemini-2.5-flash, gemini-3-flash
- ⚡ Improved MCP Integration: Optimized async layer initialization
- 📈 Performance Improvements: Reduced timeouts, lazy loading, enhanced caching
- 🛡️ Error Recovery: 95% self-healing rate with exponential backoff

$3

- 🎉 Initial release
- 🏗️ 3-layer architecture implementation
- 🎨 Basic multimodal processing

---