# EyePop.ai Developer Documentation

## Developer Documentation

- [Quickstart](https://docs.eyepop.ai/developer-documentation/quickstart.md): Get your first EyePop.ai inference running in minutes
- [Concepts](https://docs.eyepop.ai/developer-documentation/platform.md): How the EyePop.ai platform fits together
- [Pops](https://docs.eyepop.ai/developer-documentation/platform/pop.md): The reusable pipeline every EyePop analysis runs through
- [Pop Object](https://docs.eyepop.ai/developer-documentation/platform/pop/pop-object.md): The shape of a Pop, and how its top-level components run
- [Components](https://docs.eyepop.ai/developer-documentation/platform/pop/pop-components.md): Every Pop component type and the attributes it accepts
- [Forwarding](https://docs.eyepop.ai/developer-documentation/platform/pop/pop-forwarding.md): Chaining Pop components, and what each one receives
- [Examples](https://docs.eyepop.ai/developer-documentation/platform/pop/pop-examples.md): Worked Pop pipelines, from a single ability to multi-stage chains
- [Abilities](https://docs.eyepop.ai/developer-documentation/platform/abilities.md): A single preconfigured vision task that returns structured output
- [Models](https://docs.eyepop.ai/developer-documentation/platform/models.md): Pretrained models available to every account, and custom models trained on your own data
- [Sources and Options](https://docs.eyepop.ai/developer-documentation/platform/sources-and-options.md): Every way to hand media to a Pop, and the options that shape how it is processed
- [Source Types](https://docs.eyepop.ai/developer-documentation/platform/sources-and-options/sources.md): Files, streams, HTTP and RTSP URLs, WebRTC, dataset assets, and image groups
- [Supported Formats](https://docs.eyepop.ai/developer-documentation/platform/sources-and-options/formats.md): The image formats, video codecs, and containers a Pop can decode
- [Source Options](https://docs.eyepop.ai/developer-documentation/platform/sources-and-options/options.md): Frame rate, region of interest, motion gating, video mode, and component parameters
- [Frame Rate](https://docs.eyepop.ai/developer-documentation/platform/sources-and-options/options/frame-rate.md): Throttle how often a video or live stream is run through the Pop
- [Region of Interest](https://docs.eyepop.ai/developer-documentation/platform/sources-and-options/options/region-of-interest.md): Crop every frame to a region before inference
- [Motion Detection](https://docs.eyepop.ai/developer-documentation/platform/sources-and-options/options/motion-detection.md): Pause inference while the scene is still
- [Video Mode](https://docs.eyepop.ai/developer-documentation/platform/sources-and-options/options/video-mode.md): Process an uploaded video while it uploads, or after
- [Live Uploads](https://docs.eyepop.ai/developer-documentation/platform/sources-and-options/options/live-uploads.md): Treat an uploaded stream as real time and drop frames to keep up
- [Component Parameters](https://docs.eyepop.ai/developer-documentation/platform/sources-and-options/options/component-parameters.md): Override a Pop component parameters for one source
- [Pop Defaults](https://docs.eyepop.ai/developer-documentation/platform/sources-and-options/pop-defaults.md): Set source options once on the Pop instead of repeating them on every source
- [Depth and World Coordinates](https://docs.eyepop.ai/developer-documentation/platform/depth-and-world-coordinates.md): Turn a Pop's predictions into positions measured in meters
- [Depth Maps](https://docs.eyepop.ai/developer-documentation/platform/depth-and-world-coordinates/depth-maps.md): The frame-level map of distance that world coordinates are back-projected from
- [Camera Calibration](https://docs.eyepop.ai/developer-documentation/platform/depth-and-world-coordinates/camera-calibration.md): Describing the lens and the pose that turn a depth map into measurable meters
- [World Coordinates](https://docs.eyepop.ai/developer-documentation/platform/depth-and-world-coordinates/world-coordinates.md): Reading a prediction's positions in meters, and the point clouds that come with them
- [Visualizing in 3D](https://docs.eyepop.ai/developer-documentation/platform/depth-and-world-coordinates/visualizing-in-3d.md): Plotting world coordinates as a 3D scene
- [Temporal Context in Videos](https://docs.eyepop.ai/developer-documentation/platform/temporal-context.md): Run cheap analysis on every frame and deep analysis only where it matters
- [Select Operators](https://docs.eyepop.ai/developer-documentation/platform/temporal-context/select-operators.md): Run deep analysis once per tracked object, on the frame that shows it best
- [Example: Make and Model Insights from Car Drive-Bys](https://docs.eyepop.ai/developer-documentation/platform/temporal-context/example-car-make-and-model.md): Name the make, model and color of every car entering and leaving a drive-through, with one VLM call per car
- [Example: Best Face-ID Vector from Walk-Bys](https://docs.eyepop.ai/developer-documentation/platform/temporal-context/example-face-id-from-walk-bys.md): Keep one face-ID vector per person walking past a camera, from the frame that shows their face best
- [Deploying](https://docs.eyepop.ai/developer-documentation/deploying.md): Choose where your Pops run
- [Cloud](https://docs.eyepop.ai/developer-documentation/deploying/cloud.md): Run Pops on EyePop-hosted infrastructure
- [Development](https://docs.eyepop.ai/developer-documentation/deploying/cloud/development.md): Iterate quickly against a transient cloud session
- [Deployment](https://docs.eyepop.ai/developer-documentation/deploying/cloud/deployment.md): Persistent, production-ready sessions with pre-loaded models
- [Private Cameras](https://docs.eyepop.ai/developer-documentation/deploying/cloud/private-cameras.md): Analyze cameras behind a firewall with EyePop cloud inference
- [On-Premise](https://docs.eyepop.ai/developer-documentation/deploying/on-premise.md): Run the EyePop runtime on your own hardware
- [VMS](https://docs.eyepop.ai/developer-documentation/deploying/vms.md): Run EyePop inside the video management system you already operate
- [Milestone XProtect](https://docs.eyepop.ai/developer-documentation/deploying/vms/milestone.md): Run EyePop vision AI inside Milestone XProtect
- [Prerequisites](https://docs.eyepop.ai/developer-documentation/deploying/vms/milestone/prerequisites.md): Stand up Milestone XProtect and the AI Bridge before installing EyePop
- [Configuration](https://docs.eyepop.ai/developer-documentation/deploying/vms/milestone/configuration.md): The .env file, AI Bridge configMaps, and the EyePop API key
- [Running Detection](https://docs.eyepop.ai/developer-documentation/deploying/vms/milestone/running-detection.md): Subscribe a camera, run EyePop inference, and see bounding boxes
- [Workflows](https://docs.eyepop.ai/developer-documentation/deploying/vms/milestone/workflows.md): Control what each camera detects with a workflow
- [CLI](https://docs.eyepop.ai/developer-documentation/cli.md): A terminal-first way to run inference, evaluate datasets, and manage resources
- [Concepts](https://docs.eyepop.ai/developer-documentation/cli/concepts.md): Targets, deployments, instances, and datasets — the words the CLI uses
- [Install And Sign In](https://docs.eyepop.ai/developer-documentation/cli/getting-started.md): Install, authenticate, and configure the CLI
- [Run Inference](https://docs.eyepop.ai/developer-documentation/cli/run.md): Run models on images, video, and datasets from the terminal
- [Persistent Deployments](https://docs.eyepop.ai/developer-documentation/cli/persistent-sessions.md): Keep a model warm behind a stable session UUID
- [On-Premise Instances](https://docs.eyepop.ai/developer-documentation/cli/on-premise.md): Install and operate the EyePop runtime on your own hardware
- [Datasets And Evaluation](https://docs.eyepop.ai/developer-documentation/cli/evaluation.md): Build datasets and score an ability against ground truth
- [Resources](https://docs.eyepop.ai/developer-documentation/cli/resources.md): Manage datasets, abilities, deployments, and sessions
- [Command Reference](https://docs.eyepop.ai/developer-documentation/cli/reference.md): Every command and flag, generated from the CLI's built-in help.
- [Agent Skills](https://docs.eyepop.ai/developer-documentation/agent-skills.md): Install the eyepop skill for your preferred agent harness
- [SDKs](https://docs.eyepop.ai/developer-documentation/sdks.md): Official EyePop.ai client libraries
- [Python](https://docs.eyepop.ai/developer-documentation/sdks/python.md): Call EyePop from Python
- [Configuration](https://docs.eyepop.ai/developer-documentation/sdks/python/configuration.md): Credentials and environment variables
- [Running Inference](https://docs.eyepop.ai/developer-documentation/sdks/python/inference.md): Process files, streams, URLs, video, and image groups
- [Composable Pops](https://docs.eyepop.ai/developer-documentation/sdks/python/composable-pops.md): Build a Pop with the Python types
- [Data Endpoint](https://docs.eyepop.ai/developer-documentation/sdks/python/data-endpoint.md): Datasets, VLM inference, and batch evaluation
- [Node](https://docs.eyepop.ai/developer-documentation/sdks/node.md): Call EyePop from Node, the browser, and React Native
- [Configuration](https://docs.eyepop.ai/developer-documentation/sdks/node/configuration.md): Credentials and session options
- [Running Inference](https://docs.eyepop.ai/developer-documentation/sdks/node/inference.md): Files, streams, URLs, and image groups
- [Composable Pops](https://docs.eyepop.ai/developer-documentation/sdks/node/composable-pops.md): Build a Pop with the Node types
- [Visualization](https://docs.eyepop.ai/developer-documentation/sdks/node/visualization.md): Draw predictions on an HTML canvas
- [API Keys](https://docs.eyepop.ai/developer-documentation/api-keys.md): Create, store, and safely hand out EyePop credentials
- [Pricing](https://docs.eyepop.ai/developer-documentation/pricing.md): Cloud and on-premise plans
- [Workflows](https://docs.eyepop.ai/developer-documentation/workflows.md): Chain abilities into visual pipelines from the dashboard
- [Train Your Own Model](https://docs.eyepop.ai/developer-documentation/train-your-own-model.md): Build a custom ability from your own labeled data
- [Defining Your Computer Vision Model](https://docs.eyepop.ai/developer-documentation/train-your-own-model/defining-your-computer-vision-model.md): Pick a model type and scope the problem it solves
- [Example Use Case: Detecting Eyeglasses](https://docs.eyepop.ai/developer-documentation/train-your-own-model/example-use-case-detecting-eyeglasses.md): A worked example — training a model to spot eyeglasses in ad images
- [Preparing & Uploading Data](https://docs.eyepop.ai/developer-documentation/train-your-own-model/preparing-and-uploading-data.md): Collect, format, and upload the images your model learns from
- [Using EyePop.ai’s AutoLabeler](https://docs.eyepop.ai/developer-documentation/train-your-own-model/using-eyepop.ais-autolabeler.md): Test a prompt, then let the AutoLabeler pre-label your dataset
- [Human Review](https://docs.eyepop.ai/developer-documentation/train-your-own-model/human-review.md): Correct the AutoLabeler and accept the labels that train your model
- [Data Augmentation](https://docs.eyepop.ai/developer-documentation/train-your-own-model/data-augmentation-setup.md): How EyePop broadens your dataset before training
- [Training in Progress](https://docs.eyepop.ai/developer-documentation/train-your-own-model/training-in-progress.md): What happens while your model trains, and how to read its metrics
- [Deployment](https://docs.eyepop.ai/developer-documentation/train-your-own-model/deployment.md): Publish the trained model so your Pops can run it
- [Previewing Results](https://docs.eyepop.ai/developer-documentation/train-your-own-model/previewing-results.md): Test the model on real images and read its predictions
- [Iterative Training](https://docs.eyepop.ai/developer-documentation/train-your-own-model/iterative-training.md): Find weaknesses, add data, and retrain until accuracy holds
- [Deep Dives (FAQ)](https://docs.eyepop.ai/developer-documentation/train-your-own-model/deep-dives-faq.md): Answers to the questions that come up during training