Maricusco Trading Platform¶

Enterprise-grade multi-agent AI system for intelligent market analysis and trading decisions.

Python 3.12 LangGraph Docker Ready

Quick Start¶

Installation

Get started in under 5 minutes with uv package manager

git clone https://github.com/Maricusco/multi-agent-trading.git
cd multi-agent-trading
make quickstart

Developer Onboarding

Configuration

Configure LLM providers and data sources with environment variables
```
export OPENAI_API_KEY=your_key_here
export ALPHA_VANTAGE_API_KEY=your_key_here
maricusco
```
Config Reference
Mock Mode

Cost-free development and testing without LLM API calls
```
export MARICUSCO_MOCK_MODE=true
maricusco
```
Mock Mode Guide
Docker Deployment

Production-ready containerized deployment with all services
```
docker-compose up -d
docker exec -it maricusco-app maricusco
```
Docker Setup

Key Features¶

Multi-Agent Collaboration

Specialized agents collaborate through LangGraph workflows with built-in memory and state management

Parallel Execution

Independent analysts execute concurrently, reducing total execution time by 2-4x with automatic synchronization

Debate-Based Decisions

Agents engage in structured multi-round debates to refine investment theses and challenge assumptions

Vector Memory System

ChromaDB-powered memory enables agents to learn from past decisions and retrieve relevant historical context

Risk Assessment

Multi-perspective risk analysis with aggressive, conservative, and neutral debate agents

System Architecture¶

The system employs a modular monolith architecture with clear separation of concerns, enabling scalable development and future microservices migration.

graph TB
    subgraph "Analyst Team (Parallel)"
        A1[Fundamentals Analyst]
        A2[Sentiment Analyst]
        A3[News Analyst]
        A4[Technical Analyst]
    end

    subgraph "Research Team (Debate)"
        R1[Bull Researcher]
        R2[Bear Researcher]
        R3[Research Manager]
    end

    subgraph "Risk Management (Debate)"
        D1[Aggressive Debator]
        D2[Conservative Debator]
        D3[Neutral Debator]
        D4[Risk Manager]
    end

    T[Trader Agent]

    A1 & A2 & A3 & A4 --> R1 & R2
    R1 & R2 --> R3
    R3 --> T
    T --> D1 & D2 & D3
    D1 & D2 & D3 --> D4
    D4 --> Final[Final Trading Plan]

    style A1 fill:#9B8AAB,stroke:#8B7A9B,color:#fff
    style A2 fill:#9B8AAB,stroke:#8B7A9B,color:#fff
    style A3 fill:#9B8AAB,stroke:#8B7A9B,color:#fff
    style A4 fill:#9B8AAB,stroke:#8B7A9B,color:#fff
    style R1 fill:#7A9A7A,stroke:#6B8E6B,color:#fff
    style R2 fill:#C4A484,stroke:#B49474,color:#fff
    style R3 fill:#7A9FB3,stroke:#6B8FA3,color:#fff
    style T fill:#9B8AAB,stroke:#8B7A9B,color:#fff
    style D1 fill:#C4A484,stroke:#B49474,color:#fff
    style D2 fill:#7A9FB3,stroke:#6B8FA3,color:#fff
    style D3 fill:#9B8AAB,stroke:#8B7A9B,color:#fff
    style D4 fill:#7A9A7A,stroke:#6B8E6B,color:#fff
    style Final fill:#C4A484,stroke:#B49474,color:#fff