diff --git a/AI projects/Requirements.txt b/AI projects/Requirements.txt
new file mode 100644
index 0000000..6b0a150
--- /dev/null
+++ b/AI projects/Requirements.txt	
@@ -0,0 +1,4 @@
+numpy>=1.22
+pandas>=1.4
+scikit-learn>=1.1
+joblib>=1.2
\ No newline at end of file
diff --git a/AI projects/Weather Predictor/Data/sample_weather.csv b/AI projects/Weather Predictor/Data/sample_weather.csv
new file mode 100644
index 0000000..3749679
--- /dev/null
+++ b/AI projects/Weather Predictor/Data/sample_weather.csv	
@@ -0,0 +1,3 @@
+temp_prev , humidity_prev , wind_speed_prev , day_of_year , target_temp
+25.0 , 60 , 5.2 , 100 , 26.3
+24.5 , 63 , 6.1 , 101 , 25.7
diff --git a/AI projects/Weather Predictor/Readme.md b/AI projects/Weather Predictor/Readme.md
new file mode 100644
index 0000000..46ce324
--- /dev/null
+++ b/AI projects/Weather Predictor/Readme.md	
@@ -0,0 +1,20 @@
+# Weather Predictor (example AI project)
+
+**Category:** Regression / machine learning  
+**Language:** Python
+
+## Overview
+A small example project that demonstrates how to build a simple temperature predictor using scikit-learn.
+
+## Contents
+- `weather_predictor.py` - main script with train/predict subcommands
+- `data/sample_weather.csv` - small sample dataset
+- `requirements.txt` - Python dependencies
+
+## Setup
+Create a virtual environment and install dependencies:
+
+```bash
+python -m venv venv
+source venv/bin/activate        # Windows: venv\Scripts\activate
+pip install -r requirements.txt
diff --git a/AI projects/Weather Predictor/weather_predictor.py b/AI projects/Weather Predictor/weather_predictor.py
new file mode 100644
index 0000000..d8492a5
--- /dev/null
+++ b/AI projects/Weather Predictor/weather_predictor.py	
@@ -0,0 +1,80 @@
+"""
+Weather Predictor - simple regression example using scikit-learn.
+
+This script demonstrates:
+- loading CSV data (features and target)
+- splitting train/test
+- training a simple RandomForestRegressor (or LinearRegression)
+- saving the model with joblib
+- making predictions from a CSV of new inputs
+"""
+
+import os
+import argparse
+import pandas as pd
+import numpy as np
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import mean_squared_error
+import joblib
+
+DEFAULT_MODEL = "weather_model.joblib"
+
+def load_data(csv_path):
+    """
+    Expected CSV columns example:
+    temp_prev, humidity_prev, wind_speed_prev, day_of_year, target_temp
+    """
+    df = pd.read_csv(csv_path)
+    # simple check
+    if 'target_temp' not in df.columns:
+        raise ValueError("CSV must contain a 'target_temp' column as target.")
+    X = df.drop(columns=['target_temp'])
+    y = df['target_temp']
+    return X, y
+
+def train(csv_path, out_model=DEFAULT_MODEL):
+    X, y = load_data(csv_path)
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    model = RandomForestRegressor(n_estimators=100, random_state=42)
+    model.fit(X_train, y_train)
+    preds = model.predict(X_test)
+    mse = mean_squared_error(y_test, preds)
+    print(f"Trained model. Test MSE: {mse:.4f}")
+    joblib.dump(model, out_model)
+    print(f"Saved model to: {out_model}")
+
+def predict(model_path, inputs_csv, out_csv=None):
+    model = joblib.load(model_path)
+    X_new = pd.read_csv(inputs_csv)
+    preds = model.predict(X_new)
+    X_new['predicted_temp'] = preds
+    if out_csv:
+        X_new.to_csv(out_csv, index=False)
+        print(f"Saved predictions to: {out_csv}")
+    else:
+        print(X_new)
+
+def main():
+    parser = argparse.ArgumentParser(description="Weather Predictor (simple example)")
+    sub = parser.add_subparsers(dest="cmd", required=True)
+
+    t = sub.add_parser("train", help="Train model from CSV")
+    t.add_argument("--data", required=True, help="CSV file with training data")
+    t.add_argument("--out", default=DEFAULT_MODEL, help="Output model path")
+
+    p = sub.add_parser("predict", help="Predict using trained model")
+    p.add_argument("--model", required=True, help="Path to trained model (.joblib)")
+    p.add_argument("--input", required=True, help="CSV file with feature rows to predict")
+    p.add_argument("--out", default=None, help="Optional output CSV for predictions")
+
+    args = parser.parse_args()
+    if args.cmd == "train":
+        train(args.data, args.out)
+    elif args.cmd == "predict":
+        predict(args.model, args.input, args.out)
+    else:
+        parser.print_help()
+
+if __name__ == "__main__":
+    main()
diff --git a/PyVerse b/PyVerse
new file mode 160000
index 0000000..62780b7
--- /dev/null
+++ b/PyVerse
@@ -0,0 +1 @@
+Subproject commit 62780b7a031975d4710caa1485a622982f9ea20a