#80 · Primary category: Computer Vision
MaaFramework
An automation black-box testing framework based on image recognition
Project last updated:08/28/26
GitHub Stars
4.7K
Forks
543
Contributors
113
License
LGPL-3.0
Why we included this project
Automating a desktop game or app usually means driving it through a long sequence of on-screen states, and this framework is built for exactly that. It grew out of the MaaAssistantArknights project and was rewritten as a general-purpose, low-code automation core: you describe what to look for and what to click in a pipeline protocol, and it does the rest with template matching and OCR on captured frames. The core is written in C++, but bindings for Python, Node.js, Go, Rust, and C# let teams plug it into an existing stack without rewriting everything. It targets developers building black-box test suites and bot-like automation for GUI applications, especially where there is no internal API to hook into and the screen is the only interface. Simple flows stay readable in the low-code pipeline, while custom recognizers and actions leave room for the complex cases.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)