diff --git a/remove_duplicates.py b/remove_duplicates.py
new file mode 100644
index 0000000..d22f0e6
--- /dev/null
+++ b/remove_duplicates.py
@@ -0,0 +1,30 @@
+import json
+
+# Load data from nodes.json
+with open('nodes.json') as f:
+    data = json.load(f)
+
+# Function to remove duplicate nodes
+def remove_duplicates(data):
+    seen_identifiers = set()
+    unique_data = []
+    for node in data:
+        identifier = node['identifier']
+        if identifier not in seen_identifiers:
+            seen_identifiers.add(identifier)
+            unique_data.append(node)
+    return unique_data
+
+# Remove duplicates
+unique_data = remove_duplicates(data)
+
+# Check if any nodes were removed
+if len(unique_data) < len(data):
+    print("Duplicate nodes removed.")
+
+    # Save updated data back to nodes.json
+    with open('nodes.json', 'w') as f:
+        json.dump(unique_data, f, indent=4)
+else:
+    print("No duplicate nodes found.")
+
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..c87a0a0
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1 @@
+json
\ No newline at end of file