Architecture

System Overview

The system follows a modular, microservices-oriented architecture with clear separation of concerns:

┌─────────────────────────────────────────────────────────────────┐
│                        CRED Agent AI                            │
├─────────────────────────────────────────────────────────────────┤
│  ┌─────────────────┐  ┌─────────────────┐  ┌─────────────────┐  │
│  │   Slack Module  │  │   Teams Module  │  │  GraphQL API    │  │
│  │   (Controller)  │  │   (Controller)  │  │   (Controller)  │  │
│  └─────────┬───────┘  └─────────┬───────┘  └─────────┬───────┘  │
│            │                    │                    │          │
│            └────────────────────┼────────────────────┘          │
│                                 │                               │
│  ┌─────────────────────────────────────────────────────────────┐ │
│  │              Message Processing Layer                       │ │
│  │  ┌─────────────────┐  ┌─────────────────┐  ┌─────────────┐ │ │
│  │  │ Messages Service│  │ LLM Processor   │  │ File        │ │ │
│  │  │                 │  │ Service         │  │ Processor   │ │ │
│  │  └─────────────────┘  └─────────────────┘  └─────────────┘ │ │
│  └─────────────────────────────────────────────────────────────┘ │
│                                                                 │
│  ┌─────────────────────────────────────────────────────────────┐ │
│  │              AI & Processing Layer                           │ │
│  │  ┌─────────────────┐  ┌─────────────────┐  ┌─────────────┐ │ │
│  │  │ Claude          │  │ MCP Connector   │  │ OpenAI      │ │ │
│  │  │ Connector       │  │                 │  │ Connector   │ │ │
│  │  └─────────────────┘  └─────────────────┘  └─────────────┘ │ │
│  └─────────────────────────────────────────────────────────────┘ │
│                                                                 │
│  ┌─────────────────────────────────────────────────────────────┐ │
│  │              Data & Storage Layer                           │ │
│  │  ┌─────────────────┐  ┌─────────────────┐  ┌─────────────┐ │ │
│  │  │ PostgreSQL      │  │ Google Cloud    │  │ File        │ │ │
│  │  │ Database        │  │ Storage         │  │ Import      │ │ │
│  │  └─────────────────┘  └─────────────────┘  └─────────────┘ │ │
│  └─────────────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────────┘

Core Design Principles

1. Modularity - Each platform integration is isolated in its own module
2. Scalability - Stateless design with external storage
3. Extensibility - Easy addition of new platforms and processors
4. Reliability - Comprehensive error handling and retry mechanisms
5. Security - JWT-based authentication and secure token management

---

Core Modules

Messages Module (src/messages/)

Central message processing orchestrator.

Key Components:

• MessagesService - Main orchestrator for message processing
• TextProcessor - Handles text content preprocessing
• DatabaseConversationHistoryAdapter - Manages conversation persistence

Features:

• Debug mode support ([debug], [info] flags)
• Conversation history management
• Message threading support
• Token usage tracking

LLM Processor Module (src/llm-processor/)

Handles all AI-related processing.

Key Components:

Component	Purpose
LLMProcessorService	Main LLM processing coordinator
FileProcessorService	Processes files for AI consumption
CSVProcessorService	CSV processing with LangChain
ExcelProcessorService	Excel file processing
AudioProcessorService	Audio transcription with Whisper

Claude Connector (src/connectors/claude/)

Direct integration with Anthropic's Claude AI.

• Claude Sonnet 4 model integration
• Tool calling with MCP integration
• Streaming response processing
• System prompt customization per platform

MCP Connector (src/connectors/mcp/)

Model Context Protocol integration.

• Multi-server MCP client support
• JWT-based authentication
• Tool discovery and execution
• HTTP transport with custom headers