Canonical native screen, mouse, keyboard, timing, window-scoping, and media-capture component for OpenAdapt Desktop and Flow.
-
Updated
Aug 28, 2026 - Python
Canonical native screen, mouse, keyboard, timing, window-scoping, and media-capture component for OpenAdapt Desktop and Flow.
OpenAdapt’s open-source ML toolkit for training and evaluating general multimodal GUI-action models.
Desktop cockpit for local recording, qualification, execution, evidence review, and governed repair.
PII/PHI detection and redaction for GUI automation data (text, images, dicts)
Local agent bridge for governed OpenAdapt workflows, attended actions, MCP, and Agent Skills
Evaluation infrastructure for GUI agent benchmarks
Multimodal demo retrieval for GUI automation
HTML viewer components for ML dashboards and benchmarks
Temporal smoothing for UI element detection with OmniParser integration
Add a description, image, and links to the openadapt topic page so that developers can more easily learn about it.
To associate your repository with the openadapt topic, visit your repo's landing page and select "manage topics."