With the rapid expansion of digital communication networks, ensuring cybersecurity and maintaining network integrity has become a critical challenge. Traditional intrusion detection systems rely on static rules, making them ineffective against evolving cyber threats. This research presents a real-time network forensic analysis framework that integrates packet sniffing, traffic visualization, and anomaly detection using machine learning techniques. The proposed system utilizes Scapy for packet capture, PyShark for processing PCAP files, and the Isolation Forest algorithm for anomaly detection. The framework provides detailed insights through real-time monitoring, packet analysis, and visualization techniques such as protocol distribution, traffic volume analysis, and port monitoring. By implementing a machine learning-based detection system, our approach effectively identifies network anomalies, including SYN flood attacks, port scanning, and other suspicious activities. Experimental evaluations demonstrate the framework’s effectiveness in detecting network anomalies with high accuracy, making it a valuable asset for forensic investigations and network security monitoring.