Capture
ImplementedAcquires and indexes visual sources but does not create markup by itself.
Screph is an environment for creating AI tasks on visual data. It consists of modules for source acquisition, markup, computer-vision methods, project storage, work with code and scenario execution. Inputs, outputs and current limitations are listed for each module.
Acquires and indexes visual sources but does not create markup by itself.
Owns the main editable project and connects the visual source with domain markup.
Computer-vision methods create results and may propose markup changes. The main markup changes only when such a change is applied separately.
Edges, HSV/K-Means, GrabCut, Watershed, superpixels, contours and components, MSER/Hough, thresholding, matching, comparison and alignment, KLT, OCR, layout analysis and model-backed segmentation.
Grayscale, tone and contrast, blur, CLAHE, resize, crop, rotate and deskew, mask composition, inversion, morphology and contour extraction.
A single method, a linear sequence or a method graph. OCR requires ocr.runtime; YOLO, SAM and OmniParser require ml.runtime and model files.
The main project package uses versioned JSON and retains references to result files.
gui_elements, image_features, feature_matches, markup_groups, edges и regions.for_ai_agent file; a supported automation target separately prepares main.py.Automation Runtime reads the main project and executes a separate Python scenario. The for_ai_agent file is not its direct input, and execution does not start automatically after markup.
Image and text matching, condition waits and recorded capture for repeatable debugging.
Click, move, text input, hotkey, drag and scroll through Arduino HID, legacy serial or FakerInput Virtual HID.
Scenario launch, EVT telemetry, screen and match preview, progress and logs.
The assistant is off by default. It builds context with restricted data redacted and invokes only allowed typed actions. Images and files require explicit permission; changes are previewed and require confirmation.
Open the Assistant guide →Connects frames before and after an action, the action itself, an LLM plan, a local computer-vision run, proposed targets, review decisions and export. The original action trace remains unchanged for verification.