> For the complete documentation index, see [llms.txt](https://docs.eyepop.ai/developer-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.eyepop.ai/developer-documentation/deploying/vms.md).

# VMS

Run EyePop inside the video management system you already operate

A video management system (VMS) already records your cameras, shows them to operators, and raises alarms. An EyePop VMS integration adds EyePop vision AI to it without moving the cameras anywhere: it runs next to the VMS, takes video from the cameras the VMS manages, runs a Pop on it, and publishes the detections back into the VMS as bounding boxes and analytics events. Operators keep working in the client they know.

You choose what each camera detects with a workflow, which carries a [Pop](/developer-documentation/platform/pop.md). Inference runs in EyePop Cloud, so the host running the integration needs outbound access to EyePop and an [API key](/developer-documentation/api-keys.md).

### Supported VMS

| VMS                                                                       | Integration             | Runs as                                                       |
| ------------------------------------------------------------------------- | ----------------------- | ------------------------------------------------------------- |
| [Milestone XProtect](/developer-documentation/deploying/vms/milestone.md) | Milestone AI Bridge app | one more container in the AI Bridge Docker Compose deployment |

### Next steps

* [Milestone XProtect](/developer-documentation/deploying/vms/milestone.md) — install the EyePop app into the Milestone AI Bridge
* [Cloud](/developer-documentation/deploying/cloud.md) — call EyePop directly when no VMS sits in front of the cameras
* [Private Cameras](/developer-documentation/deploying/cloud/private-cameras.md) — cloud inference for cameras behind a firewall