okx trading

docs/skills/cex.md

@@ -0,0 +1,24 @@
+"""
+# CEX Skills Documentation
+
+CEX skills are first-class skills designed for interacting with centralized cryptocurrency exchanges like OKX. 
+
+## Using the trade_on_okx Skill
+
+1. Configure your OKX API credentials in the Agent model.
+2. Use the `trade_on_okx` skill to automatically trade cryptocurrencies based on technical indicators.
+3. Input Parameters:
+    - `symbol`: The trading pair (e.g., BTC/USDT).
+    - `timeframe`: The timeframe for the analysis (e.g., 1h).
+    - `amount`: The amount to trade.
+
+## Example
+
+```python
+from skills.cex.okx import TradeOnOkx
+
+trade_skill = TradeOnOkx(api_key, secret, password)
+trade_skill.run("BTC/USDT", timeframe="1h", amount=0.001)
+```
+
+"""

models/agent.py

@@ -1,6 +1,7 @@
 import json
 from datetime import datetime, timezone
 from typing import Any, Dict, List, Optional
+from skills.cex.okx import TradeOnOkx
 
 from epyxid import XID
 from fastapi import HTTPException
@@ -657,3 +658,23 @@ def save(self, db: Session) -> None:
             db.add(self)
 
         db.commit()
+
+def initialize_agent():
+    cex_config = {
+        "api_key": "your_okx_api_key",
+        "secret": "your_okx_secret",
+        "password": "your_okx_password",
+    }
+
+    cex_skills = {
+        "trade_on_okx": TradeOnOkx(
+            api_key=cex_config['api_key'],
+            secret=cex_config['secret'],
+            password=cex_config['password']
+        )
+    }
+
+    return {
+        "cex_skills": cex_skills,
+        "cex_config": cex_config,
+    }

skills/CEX/_init_.py

@@ -0,0 +1,13 @@
+from langchain_core.tools import BaseTool
+from skills.crestal.search_web3_services import search_web3_services
+from skills.crestal.trade_on_okx import TradeOnOkx  # Import the new skill
+
+def get_common_skill(name: str) -> BaseTool:
+    if name == "search_web3_services":
+        return search_web3_services
+    elif name == "trade_on_okx":  # Add the condition for the new tool
+        # Replace with actual OKX API credentials
+        api_key = "your_okx_api_key"
+        secret = "your_okx_secret"
+        password = "your_okx_password"
+        return TradeOnOkx(api_key, secret, password)

skills/CEX/base.py

@@ -0,0 +1,22 @@
+from langchain_core.skills import IntentKitSkill
+import ccxt
+import pandas as pd
+
+class CEXBaseSkill(IntentKitSkill):
+    """
+    Base class for all CEX (Centralized Exchange) skills. Provides shared infrastructure like the ccxt client.
+    """
+    def __init__(self, api_key: str, secret: str, password: str, exchange: str = "okx"):
+        self.exchange = ccxt.__dict__[exchange]({
+            'apiKey': api_key,
+            'secret': secret,
+            'password': password,
+            'enableRateLimit': True,
+        })
+
+    def fetch_historical_data(self, symbol, timeframe, limit=200):
+        """Fetch historical OHLCV data."""
+        ohlcv = self.exchange.fetch_ohlcv(symbol, timeframe, limit=limit)
+        df = pd.DataFrame(ohlcv, columns=['timestamp', 'open', 'high', 'low', 'close', 'volume'])
+        df['timestamp'] = pd.to_datetime(df['timestamp'], unit='ms')
+        return df

skills/CEX/okx.py

@@ -0,0 +1,70 @@
+rom .base import CEXBaseSkill
+
+class TradeOnOkx(CEXBaseSkill):
+    """
+    A skill to trade cryptocurrencies on OKX using RSI, CCI, Bollinger Bands, and EMA 200 indicators.
+    """
+    name = "trade_on_okx"
+    description = "Automatically trade crypto on OKX using technical indicators for decision-making."
+
+    def calculate_indicators(self, df):
+        """Calculate RSI, CCI, Bollinger Bands, and EMA 200."""
+        df['rsi'] = self.calculate_rsi(df['close'], period=14)
+        df['cci'] = self.calculate_cci(df, period=20)
+        df['ema_200'] = df['close'].ewm(span=200).mean()
+        df['bollinger_mid'] = df['close'].rolling(window=20).mean()
+        df['bollinger_std'] = df['close'].rolling(window=20).std()
+        df['bollinger_upper'] = df['bollinger_mid'] + (df['bollinger_std'] * 2)
+        df['bollinger_lower'] = df['bollinger_mid'] - (df['bollinger_std'] * 2)
+        return df
+
+    @staticmethod
+    def calculate_rsi(series, period):
+        """Calculate the Relative Strength Index (RSI)."""
+        delta = series.diff()
+        gain = (delta.where(delta > 0, 0)).rolling(window=period).mean()
+        loss = (-delta.where(delta < 0, 0)).rolling(window=period).mean()
+        rs = gain / loss
+        return 100 - (100 / (1 + rs))
+
+    @staticmethod
+    def calculate_cci(df, period):
+        """Calculate the Commodity Channel Index (CCI)."""
+        tp = (df['high'] + df['low'] + df['close']) / 3
+        ma = tp.rolling(window=period).mean()
+        md = tp.rolling(window=period).apply(lambda x: np.fabs(x - x.mean()).mean())
+        cci = (tp - ma) / (0.015 * md)
+        return cci
+
+    def determine_signal(self, df):
+        """Determine buy/sell signals based on indicators."""
+        latest = df.iloc[-1]
+
+        if (
+            latest['rsi'] < 30
+            and latest['cci'] < -100
+            and latest['close'] < latest['bollinger_lower']
+            and latest['close'] > latest['ema_200']
+        ):
+            return 'buy'
+
+        if (
+            latest['rsi'] > 70
+            and latest['cci'] > 100
+            and latest['close'] > latest['bollinger_upper']
+            and latest['close'] < latest['ema_200']
+        ):
+            return 'sell'
+
+        return 'hold'
+
+    def execute_trade(self, symbol, signal, amount):
+        """Execute a trade on OKX."""
+        if signal == 'buy':
+            order = self.exchange.create_market_buy_order(symbol, amount)
+            print(f"Buy order executed: {order}")
+        elif signal == 'sell':
+            order = self.exchange.create_market_sell_order(symbol, amount)
+            print(f"Sell order executed: {order}")
+        else:
+            print("No trade executed.")