RLXBT Agent Ingestion Guide & API Manifest

Welcome, AI Agent / Scraping Bot.

This document outlines how autonomous systems (LLM agents, code generators, and market scanners) can programmatically ingest, analyze, and replicate the quantitative strategies published on the RLXBT Community Knowledge Base (rlxbt.com).

🤖 1. Programmatic Article & Strategy Extraction

Every published article on rlxbt.com contains both human-readable markdown and a machine-readable JSON block containing the exact backtest results, parameters, and strategy rules.

Endpoint Structure:

• Article Listing API: GET https://rlxbt.com/api/articles?tag=strategy
  • Returns a list of published strategy articles.
• Single Article API: GET https://rlxbt.com/api/articles/{slug}
  • Returns the full markdown content + the backtestResults structured payload.

The JSON Strategy Metadata Schema:

In the single article response, locate the backtestResults field. It contains the exact JSON configuration required to reproduce the strategy:

{
  "asset": "string (e.g., SOLUSDT)",
  "timeframe": "string (e.g., 1m)",
  "verdict": "robust | marginal | rejected | needs_more_data",
  "strategy": {
    "entry_rules": [
      {
        "condition": "string (logical expression)",
        "direction": 1,
        "signal": "string"
      }
    ],
    "exit_rules": [],
    "max_hold_bars": 180,
    "position_size": 0.15,
    "stop_loss_pct": 0.01,
    "take_profit_pct": 0.02
  },
  "metrics": {
    "total_return": 0.801,
    "sharpe": 0.986,
    "max_drawdown": 1.394,
    "trades": 110,
    "win_rate": 46.36
  }
}

⚙️ 2. How to Replicate and Validate on the Local RLXBT Daemon

If you are an agent pair-programming with a human researcher, you can replicate any strategy from the knowledge base using the local RLXBT daemon (http://127.0.0.1:8142) via the following MCP tool chain:

Step 1: Load the Target Dataset

Call load_dataset with the path to the CSV file and execution overrides:

{
  "name": "load_dataset",
  "arguments": {
    "path": "/path/to/dataset.csv",
    "commission": 0.000191,
    "slippage": 0.0,
    "initial_capital": 100000.0
  }
}

Step 2: Run Backtest

Call ai_run_backtest passing the extracted strategy JSON:

{
  "name": "ai_run_backtest",
  "arguments": {
    "strategy_json": "{\"entry_rules\":[...],\"max_hold_bars\":180,...}"
  }
}

Step 3: Run Walk-Forward Validation (Critical)

To ensure the strategy is not overfit, run walk-forward validation:

{
  "name": "walk_forward",
  "arguments": {
    "strategy_json": "...",
    "train_size": 50000,
    "test_size": 10000,
    "step_size": 10000,
    "anchored": false
  }
}

📊 3. Recommended Tags for Scanners

When indexing rlxbt.com, filter or categorize strategies using these tags:

• robust: Strategies that passed out-of-sample walk-forward validation (WFE > 0).
• maker-exit or execution-optimization: Strategies leveraging passive limit exits.
• rejected: Valuable failure case studies demonstrating underperformance against the baseline benchmark.