Skip to content

Using CosmoEdge ​

Start with your first detection, then learn to configure scenarios, edit pipelines and integrate your models. Follow the guides in order, or choose a topic below.

Basic Use ​

GuideUse it whenFinal result
Quick Start: Deployment, Sign-In, and First DetectionDeploying or connecting for the first timeConnect a video source and view detections and recorded events
Scenario Task Configuration: Channels, Regions, Parameters, and AlarmsTurning a built-in algorithm into a business taskSave regions, parameters and schedules, then check rules with alert and non-alert examples

AI Capability Configuration ​

GuideUse it whenFinal result
VLM and DINO: Prompt-Driven Vision TasksExploring a state decision or open-vocabulary targetCheck VLM answers and DINO detections against your prompt using sample images

Advanced Extensions ​

GuideUse it whenFinal result
Pipeline Orchestration: Modify and Create PipelinesChanging a rule chain or creating new business logicSave and run a custom pipeline, then check alert rules and settings after a restart
Third-Party Model Integration: Convert, Upload, and ValidateBringing a custom model into CosmoEdgeLoad your model, view detections, and check events and continued operation
  • First experience: Quick Start → Scenario Task Configuration.
  • Long-tail requirement exploration: Scenario Task Configuration → VLM and DINO.
  • Custom business logic: Scenario Task Configuration → Pipeline Orchestration.
  • Custom model deployment: Pipeline Orchestration → Third-Party Model Integration.

Each guide includes result checks. After setup, follow the steps to check live results, event records and task behavior after a restart. Try both alert and non-alert examples to check your rules.

Engine code: Apache-2.0. Models and dependencies retain their own licenses.

CosmoEdge / Contact

Let’s talk about your edge AI project.

Model deployment, hardware selection or system integration—start with the question you’re working on.

Business & project enquiries

hello@cosmowander.ai
Email us

Installation, usage and open-source questionsVisit community discussions
What should I include?

Share what you know; we can work through the remaining details together.

  • Use case

    What to detect and how events will be used

  • Existing setup

    Existing models, hardware or systems

  • Workload

    Stream count, frequency and latency needs

  • Project stage

    Your project stage and immediate questions