AppAgent is an LLM-based multimodal agent framework designed to operate smartphone applications without manual scripting. It integrates screen capture, GUI element detection, OCR parsing, and natural language planning to understand app layouts and user intents. The framework issues touch events (tap, swipe, text input) through an Android device or emulator to automate workflows. Researchers and developers can customize prompts, configure LLM APIs, and extend modules to support new apps and tasks, achieving adaptive and scalable mobile automation.

TurboDoc is an AI-powered invoice processing tool designed to streamline the extraction and transformation of unstructured data from invoices and receipts into organized, structured formats. With advanced OCR technology, it captures essential details such as vendor information, total amounts, dates, and more, ensuring rapid and accurate data extraction. This reduces manual data entry errors, saves time, and improves business efficiency by offering a user-friendly interface and secure data storage with AES256 encryption. TurboDoc supports multiple languages, making it a versatile solution for various business needs.