Browse Code
Vanga reads a screen — live or captured — and resolves it to an action. You describe the interface in plain YAML: tokens are pictures matched under a discipline, lexemes their spatial arrangements, with OCR for the content that changes. On a match it drives the GUI (click, type, route text); the logic turns a recognized screen into what to do — a watched value with prose rules, or a neighbourhood rule table over a tiled grid. The shipped examples are pure grammar, no Java: a calculator automator and a Minesweeper solver. Java 21, MIT-licensed. See VANGA_DESIGN.md.
Features
- Recognize GUI screens from pixels
- Describe screens in plain YAML — no code required
- OCR reads the content that changes
- Solve tiled UIs with neighbourhood rules (e.g. Minesweeper)
- Drives the live pointer and restores it after acting
License
MIT LicenseOther Useful Business Software
Ship Agents Faster
Gemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Vanga!
