Percia

Enables a local model to watch Wyze cameras and detect people, pets, packages, and intruders, with credentials kept in the OS keychain.

Provides visual recognition and PTZ camera control for DIY MOSS (ESP32) smart assistants, bridging cloud AI with local camera capabilities via WebSocket.

Enables AI clients to list configured cameras, fetch current JPEG frames from video files, webcams, or RTSP/HTTP streams, run local YOLO object detection, and count objects inside named polygonal zones using normalized coordinates. Answers come back as compact JSON with timestamps and image age, so a model can respond to questions like "Is anyone there?" or "How many cars are parked?" while only requesting the actual image when needed.

Enables AI agents to perceive and quantitatively verify physical hardware through USB webcams and RTSP/HTTP network streams, returning inline image content plus numerical metrics such as brightness, contrast, edge density, motion, SSIM baseline comparisons, and OCR text. Agents can watch feeds for visual conditions, correlate buffered frames with serial/log/MQTT events, and apply privacy masks and access controls.