0xLuigi is an intelligent crypto recommendation engine, built upon the sophisticated agent orchestration that has powered Strawberry AI since its inception.

This section breaks down the key components that drive Luigi’s inner workings, enabling it to deliver real-time crypto insights and recommendations on Telegram and Twitter.

​
The Classification Engine

The Classification Engine is a specialized agent responsible for extracting and categorizing crucial data from incoming Twitter and Telegram messages. Its core functions include:

Narrative Detection

  • Determines overarching themes based on context.
  • Examples: DeFi, AI Agents, DeFAI, Lending, etc. Entity Extraction
  • Identifies references to crypto projects.
  • Example: Recognizing “@StrawberryAI_5” as BERRY using an internal lookup table. Ticker Extraction
  • Detects and infers crypto tickers such as BERRY, ETH,andETH, and BTC, even if they are not explicitly mentioned, leveraging similarity search and contextual analysis. Sentiment Analysis
  • Assigns sentiment scores (0 = bearish, 10 = bullish) to identified narratives, projects, and tickers. Each sentiment score includes a confidence level (0 to 1, with decimal precision). All extracted data is then processed by the Big Data Engine for deeper analysis.

The Classification Engine operates autonomously, running 24/7, continuously analyzing and adapting based on evolving market trends. Its watchlist of key opinion leaders (KOLs) is dynamically updated, ensuring that Luigi prioritizes sources with a strong track record of accurate insights.

Furthermore, the engine employs a self-improving feedback loop, refining its classifications based on historical performance. This continuous learning process enhances Luigi’s ability to detect patterns, leading to increasingly precise recommendations.

​
The Big Data Engine

The Big Data Engine serves as Luigi’s analytical core, processing vast amounts of time-series data to stay ahead of market trends. In crypto, narratives and market buzz evolve rapidly, requiring real-time adaptation. The Big Data Engine utilizes a proprietary algorithm that updates rankings every second to reflect emerging market dynamics. It optimizes for key factors, including: Novelty Detection – Identifying new and emerging trends. Trend Analysis – Recognizing momentum shifts. Narrative Rankings – Prioritizing dominant themes. Ticker Rankings – Assessing sentiment, correlation, and trend strength.

By continuously refining these metrics, the Big Data Engine ensures that Luigi delivers insights based on the freshest and most relevant market intelligence.

​
The Reasoning Engine

The Reasoning Engine is responsible for final decision-making, distilling large datasets into actionable recommendations.

  • Every hour, it ingests the latest snapshot from the Big Data Engine, processing over 100 ranked tickers and more than 2 million tokens per run.
  • To handle this volume, it operates through a recursive agent loop:
    • For each ranked ticker, it performs an in-depth analysis to generate a “worth buying” score (0 to 10).
    • The top 10 scoring tickers proceed to the final evaluation phase.
    • This phase incorporates real-time market data, sentiment analysis, social chatter, and external web-sourced insights.
  • Ultimately, the process results in 1 to 3 recommended picks per hour.

To ensure transparency and continuous learning, Luigi maintains a detailed diary of all reasoning data, tracking both successful and unsuccessful recommendations. This log serves as a foundation for future improvements. Finally, Luigi condenses its insights into concise, digestible updates for simultaneous posting on Twitter and Telegram, ensuring that users receive real-time, high-quality crypto recommendations.