Stop Trading Like It's 1999: I Built an Autonomous, Vision-Capable Crypto Bot with Python 3.13 🚀

Source: Dev.to

Meet LLM_Trader v2

An autonomous, vision‑capable trading engine that turns market data, news, and chart context into structured BUY / SELL / HOLD / UPDATE decisions.

LLM_Trader v2 in action.

🏗️ The Architecture: A “Brain” for the Markets

Most AI bots fail because they simply dump raw numbers into a prompt. LLM_Trader v2 uses a sophisticated multi‑stage pipeline designed for confluence.

The Muscles (Market Data)

• Aggregates data from 5+ major exchanges (Binance, KuCoin, Gate.io, MEXC, Hyperliquid) via ccxt.
• Analyzes:
  • Technical Indicators – custom engine built from scratch (no pandas‑ta).
  • Order‑book depth & spread.
  • Trade flow (buy/sell ratio, trade velocity).
  • Funding rates for perpetual futures.
  • OHLCV across 7 timeframes: 4 h, 12 h, 24 h, 3 d, 7 d, 30 d, 365 d.

The Eyes (Vision Engine)

• Renders a ~150‑candlestick chart with Plotly, optimized for AI pattern recognition.
• Sends the image directly to vision models (Gemini Flash) for visual pattern analysis—because sometimes a chart pattern is worth a thousand RSI readings.

The Ears (RAG Engine)

• Pulls real‑time news via CryptoCompare.
• Processes with wtpsplit for neural sentence segmentation.
• Extracts key facts and numbers, filtering noise to give the LLM a “ground truth” of current events—not just headlines, but data‑rich sentences.

The Brain (Model Manager)

• Orchestrates textual data, visual charts, news snippets, and market metrics.
• Toggles between Google Gemini, Claude (via OpenRouter), or local models via LM Studio.

🧠 From “Chat” to “Execution”: The PositionExtractor (New Feature in v2)

The magic isn’t just in the prompt—it’s in the parsing. PositionExtractor uses standardized regex patterns to consistently extract:

• Action – BUY / SELL / HOLD / CLOSE
• Confidence – HIGH / MEDIUM / LOW (mapped to position sizing)
• Rationale – Structured explanation logged for future “Trading Brain” learning.

📊 What the AI Actually Sees (Real Example)

Below is a snapshot of what gets sent to the AI for a single analysis cycle:

TRADING CONTEXT:
  - Symbol: BTC/USDC
  - Current Price: $87,499
  - Fear & Greed Index: 24 (Extreme Fear) – 7‑day history

MARKET OVERVIEW:
  - Total Market Cap: $3.88T | BTC Dominance: 56.52%
  - Order Book Imbalance: +0.180 (Moderate Buy Pressure)
  - Buy/Sell Ratio: 0.16 (Strong Selling)

TECHNICAL ANALYSIS (4h):
  - RSI: 46.65 | MACD Histogram: +112.46
  - ADX: 12.86 | Stochastic: 60.02/73.78
  - Death Cross Active (20 SMA

• Discord: Join our Development Chat

Disclaimer: This software is for educational purposes. Crypto trading involves high risk. Always paper‑trade first.