OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Infrastructure & Serving

Hub — securade

Hub — securade is a self-hosted Python application that uses natural-language descriptions and generative AI to train or fine-tune computer-vision models for CCTV feeds. It supports edge deployment, with documented monitoring functions including PPE detection, proximity alerts and exclusion-zone monitoring.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Hub — securade — OpenViST project profile in AI Infrastructure & Serving.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use HUB when you have CCTV feeds and want to configure camera-specific computer-vision monitoring on a self-hosted server or edge device, especially for workplace safety checks.

Who it is for

  • Teams operating CCTV cameras that need custom computer-vision detection for individual feeds.
  • Developers or system administrators deploying vision workloads on a server or edge device.
  • Industrial and workplace safety teams seeking camera-based PPE, proximity or restricted-area monitoring.

Documented uses

  • Train or fine-tune a detection model from a natural-language description without manual data labelling.
  • Configure CCTV cameras and monitoring policies through the Streamlit web application.
  • Monitor feeds for PPE compliance, worker proximity to machinery or vehicles, and activity in exclusion zones.
  • View real-time safety metrics and receive Telegram notifications for detected violations.
Before you choose

Requirements & limits

The public repository specifies the AGPL-3.0 license. Its README says a commercial license is needed to bundle and distribute the software.

  • The documented workflow targets a custom model per camera feed rather than a single generic CCTV detector.
  • The README lists D-Link, Tapo, TP-Link, Axis and HikVision cameras as supported.
  • NVIDIA Jetson installation requires matching JetPack, CUDA, cuDNN, PyTorch and Torchvision versions; the README describes a minimum of 8 GB memory for Jetson devices.
  • The command-line options include CPU inference using OpenVINO Runtime.
  • The README describes edge processing without cloud dependency and automatic face masking.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install HUB and start its Streamlit server

Install the Python application, prepare its Streamlit configuration files and start the server for camera and policy configuration.

Before you start

  • A server or self-hosted environment with Python and pip.
  • The HUB repository and its requirements.txt file.
  • The repository's config.toml and secrets.toml files.

Steps

  1. Clone https://github.com/securade/hub.git, enter the hub directory, create and activate a virtual environment, then install dependencies with pip install -r requirements.txt.

  2. Create a .streamlit directory and copy config.toml and secrets.toml into it.

  3. Run python securade.py --server to start the web server.

  4. Use the server interface to configure CCTV cameras and policies.

Expected outcome

The README describes a running Streamlit application for camera and policy configuration.

Guide limitations

  • The README shows a default password of pass and says it can be changed in .streamlit/secrets.toml.
  • Jetson GPU installation involves additional JetPack, CUDA, cuDNN, PyTorch and Torchvision version requirements.
  • This setup sequence does not document the full process for configuring a camera feed or training a model.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
8 October 2026
Original website title
securade/hub · Official homepage title · retained in its source language
How we review sourcesSuggest a correction