SharpAI Dev Team
Official@sharpai · Silicon Valley
SharpAI empowers your traditional CCTV/NVR and surveillance cameras with machine learning technologies.
Agent Skills by SharpAI Dev Team
Showing 25 vetted skills indexed across 1 GitHub repositories.
Cloud Provider Regression Test
Tests cloud LLM providers for connectivity, chat, JSON output, and SSE streaming.
segmentation-sam2
Generates pixel-level object masks from point and box prompts using Segment Anything 2.
model-training
Fine-tune YOLO models on COCO datasets and export to TensorRT, CoreML, or ONNX.
annotation-data
Manages annotation datasets with CRUD operations, label tracking, and COCO-format export.
yolo-detection-2026-openvino
Detects objects in camera frames using YOLO models on Intel OpenVINO devices via Docker.
yolo-detection-2026-coral-tpu-win-wsl
Detects objects in camera frames on Google Coral Edge TPU via Windows WSL.
yolo-detection-2026-coral-tpu-macos
Detects objects in camera frames using Google Coral Edge TPU hardware acceleration.
camera-provider-tapo
Integrate TP-Link Tapo cameras via RTSP and ONVIF protocols.
camera-provider-reolink
Integrate Reolink cameras via RTSP and HTTP APIs for streaming and snapshots.
camera-provider-eufy
Integrate Eufy cameras with local RTSP streaming and event-triggered clip capture.
sam2-segmentation
Segment objects in video frames using click points and Segment Anything 2 models.
SmartHome Video Anomaly Benchmark
Benchmark Visual-Language Models on smart home video anomaly detection.
Home Security AI Benchmark
Evaluates LLM and VLM models for home security AI via 143 tests in 16 categories.
HomeSafe-Bench
Benchmark Vision-Language Models on indoor home safety hazard detection.
depth-estimation
Estimate depth from monocular video frames using Depth Anything v2 models.
dataset-annotation
Annotate datasets with bounding boxes, SAM2 segmentation, and DINOv3 visual grounding.
go2rtc-cameras
Register multiple RTSP camera streams with the go2rtc WebRTC server.
homeassistant-bridge
Integrate Home Assistant camera entities with the Aegis AI platform for bidirectional data flow.
webhook-trigger
Forward Aegis events to webhook URLs with custom headers and filtering.
ha-automation-trigger
Fire custom aegis_detection events into Home Assistant from Aegis camera detections.
mqtt-automation
Publish SharpAI Aegis events to an MQTT broker with configurable topics.
yolo-detection-2026
Detect objects in video frames using YOLO 2026 models.
channel-line
Integrate an AI agent with LINE messaging platform for bidirectional text communication.
channel-matrix
Integrate an AI agent with Matrix/Element for real-time messaging.
Frequently Asked Questions About SharpAI Dev Team
FAQPage SchemaWhat specific surveillance tasks are enabled by these capabilities?▼
These capabilities enable real-time object detection, monocular depth estimation, and video frame segmentation. Users can integrate diverse camera hardware via RTSP or ONVIF, perform hazard detection using specialized benchmarks, and trigger external notifications through MQTT, webhooks, or messaging platforms like Signal and Matrix.
Which technical personas benefit from these integrations?▼
Systems engineers, home security integrators, and computer vision researchers benefit from these capabilities. The platform is designed for developers building custom surveillance ecosystems who require standardized interfaces for camera ingestion, model-based video analysis, and event-driven communication between security hardware and smart home controllers.
What are the primary dependencies for deploying these surveillance integrations?▼
Deployment requires compatible surveillance hardware supporting RTSP or ONVIF protocols and a host environment capable of running vision models. Integration with home management systems requires an active MQTT broker or a configured bridge to facilitate bidirectional data flow between the detection engine and the target environment.