AzurLaneAutoScript is a mobile game automation system designed to perform repetitive gameplay tasks unattended. It functions as a screenshot-driven bot that controls Android devices, emulators, and cloud phones via ADB and uiautomator2, using computer vision to make interaction decisions instead of fixed timers. The project distinguishes itself through an advanced computer vision suite that includes local optical character recognition and perspective-aware grid detection. These tools allow the bot to parse 3D game maps, compute vanishing points, and normalize grid-centered objects for precise
This is an open-source automation tool for the game Wuthering Waves that uses image recognition to control gameplay without modifying game memory or files. It runs automation tasks while the game window is minimized or obscured, freeing the computer for other use, and accepts command-line arguments to start specific tasks and optionally exit after completion. The tool automatically detects playable characters through screen analysis and adapts actions without manual skill configuration. It supports all common 16:9 resolutions up to 4K as well as some ultrawide formats, with a minimum required
This project is a reference library and collection of example code patterns for deploying cloud infrastructure using the AWS CDK. It provides a set of sample projects that demonstrate how to define compute, storage, and networking resources using general purpose programming languages. The library includes reference implementations for various architectural patterns, including serverless backends with GraphQL and WebSocket APIs, container orchestration with load balancers and auto-scaling, and global static website hosting via content delivery networks. It also provides designs for isolated ne
ZenlessZoneZero-OneDragon is a game automation bot designed for Zenless Zone Zero. It functions as a combat automation script, an account management orchestrator, and an AI gameplay assistant to automate combat, daily quests, and character movement. The project utilizes image and audio recognition models to implement precision combat dodging and execute attack sequences. It employs pathfinding and recognition models for automated environmental navigation and interaction within game zones. The software provides broader capabilities for automating recurring daily tasks and resource collection.