Skip to content

Redhound Internal Documentation

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/redhound-labs/redhound.git
    cd redhound
    make quickstart
    

    Developer Onboarding

  • Configuration


    Configure LLM providers and data sources with environment variables

    export OPENAI_API_KEY=your_key_here
    export REDHOUND_FMP_API_KEY=your_fmp_key_here
    make dev
    

    Config Reference

  • Docker Deployment


    Production-ready containerized deployment with all services

    make up-build   # build and start stack
    curl http://localhost:8000/health
    make up-workers # Temporal + Kafka + workers + model-server
    

    Docker Setup


Key Features

Multi-Agent Collaboration

A team of 9 specialist analysts run as parallel Temporal worker activities, each scoring the signal independently before a deterministic aggregator merges them.

Confidence-Gated Debate

Bull and bear researchers engage in structured debates to refine investment theses. A confidence gate tunes the debate to a single round when signals are already high-confidence (≥75%) and two rounds otherwise, optimizing for speed and cost. The Starter plan skips the LLM debate entirely.

Vector Memory System

pgvector-powered memory enables agents to learn from past decisions and retrieve relevant historical context for current market situations.

Deterministic Risk Overlay

A 100% deterministic risk management engine applies precise position sizing and stop-loss levels based on market volatility regime and signal confidence.

Signal Accuracy System

Entropy-based confidence scoring, VIX linear interpolation, RSI divergence detection, OBV confirmation, multi-timeframe alignment, sector rotation, and adaptive analyst weights that improve automatically over time.

Background Scanner & Screener

Continuous market scanning with configurable conditions, deterministic quick-screen (zero LLM), and automatic full-analysis for high-scoring opportunities.


System Architecture

Analysis runs as an event-driven system: the FastAPI app publishes triggers to Kafka, Temporal workers execute the pipeline, and results stream back to the browser over WebSocket. Nine analyst activities feed a deterministic signal aggregator, a confidence-gated debate, and a deterministic risk overlay — the API process never runs the pipeline in-process.

graph TB
    subgraph "Core Analysts (Parallel)"
        A1[Technical Analyst]
        A2[Fundamentals Analyst]
        A3[Sentiment Analyst]
        A4[News Analyst]
        A5[Market Context Analyst]
    end

    subgraph "Edge Analysts"
        A6[Sector Analyst]
        A7[Insider Analyst]
        A8[Earnings Revisions Analyst]
        A9[Valuation Comparables Analyst]
    end

    subgraph "Signal Processing"
        SA[Signal Aggregator]
        CG{Confidence Gate}
    end

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

    subgraph "Risk Strategy"
        D4[Risk Overlay]
    end

    A1 & A2 & A3 & A4 & A5 --> SA
    A6 & A7 & A8 & A9 --> SA
    SA --> CG
    CG -- "Medium/Low" --> R1 & R2
    CG -- "High" --> R3
    R1 & R2 --> R3
    R3 --> 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 A5 fill:#9B8AAB,stroke:#8B7A9B,color:#fff
    style A6 fill:#7A9A7A,stroke:#6B8E6B,color:#fff
    style A7 fill:#7A9A7A,stroke:#6B8E6B,color:#fff
    style A8 fill:#7A9A7A,stroke:#6B8E6B,color:#fff
    style A9 fill:#7A9A7A,stroke:#6B8E6B,color:#fff
    style SA fill:#B8A082,stroke:#A89072,color:#fff
    style CG fill:#7A9FB3,stroke:#6B8FA3,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 D4 fill:#7A9A7A,stroke:#6B8E6B,color:#fff
    style Final fill:#C4A484,stroke:#B49474,color:#fff