# How to run the official website Capsule on the client **URL:** \ **Category:** Questions\ **Created:** [April 13, 2020, 2:20am UTC](https://forum.aotu.ai/t/how-to-run-the-official-website-capsule-on-the-client/50 "2020-04-13T02:20:11Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![shao](https://avatars.discourse-cdn.com/v4/letter/s/aeb1de/32.png) [@shao](https://forum.aotu.ai/u/shao)\ **Post date:** [April 13, 2020, 2:20am UTC](https://forum.aotu.ai/t/how-to-run-the-official-website-capsule-on-the-client/50/1 "2020-04-13T02:20:11Z")
Excuse me, do you know how to run the official website Capsule on the client. I downloaded two capsules that I don’t see any class names available in the second drop-down when setting the alarm ---
**Author:** ![tyler.compton](https://sea1.discourse-cdn.com/flex019/user_avatar/forum.aotu.ai/tyler.compton/32/27_2.png) [@tyler.compton](https://forum.aotu.ai/u/tyler.compton)\ **Post date:** [April 13, 2020, 4:22am UTC](https://forum.aotu.ai/t/how-to-run-the-official-website-capsule-on-the-client/50/2 "2020-04-13T04:22:28Z")
Hi Shao, In order for the capsule to be loaded by BrainFrame, it must be put in the `capsules` directory on the computer running the server. This directory is in the same folder as the `docker-compose.yml`. Once you’ve put the capsule there, it should be available in the “Global Plugin Configuration” menu once it’s loaded. Depending on the capsule and the machine you’re using, the capsule may load very quickly or take 10-15 seconds. ---
**Author:** ![alex.thiel](https://sea1.discourse-cdn.com/flex019/user_avatar/forum.aotu.ai/alex.thiel/32/48_2.png) [@alex.thiel](https://forum.aotu.ai/u/alex.thiel)\ **Post date:** [April 13, 2020, 5:06pm UTC](https://forum.aotu.ai/t/how-to-run-the-official-website-capsule-on-the-client/50/3 "2020-04-13T17:06:19Z")
If it helps you visualize, this is the directory structure you should have: ```auto . ├── capsules │ └── YOUR_CAPSULE_HERE.cap ├── docker-compose.yml └── volumes ``` ---
**Author:** ![shao](https://avatars.discourse-cdn.com/v4/letter/s/aeb1de/32.png) [@shao](https://forum.aotu.ai/u/shao)\ **Post date:** [April 14, 2020, 1:41am UTC](https://forum.aotu.ai/t/how-to-run-the-official-website-capsule-on-the-client/50/6 "2020-04-14T01:41:36Z")
Yeah, I understand. I can also see it in the “Global Plugin Configuration” menu. ![image](https://us1.discourse-cdn.com/flex019/uploads/aotu/original/1X/7ece29ec024005e8e5c0a670fc3109f795b6200a.png) But when I set the alarm, there is no dropdown option for the condition variable, and the OK button is also gray, so I cannot complete the alarm configuration ![image](https://us1.discourse-cdn.com/flex019/uploads/aotu/original/1X/13da7362a8b82b701bbd7c33a3163112ee9d03ae.png) ---
**Author:** ![alex.thiel](https://sea1.discourse-cdn.com/flex019/user_avatar/forum.aotu.ai/alex.thiel/32/48_2.png) [@alex.thiel](https://forum.aotu.ai/u/alex.thiel)\ **Post date:** [April 14, 2020, 5:09pm UTC](https://forum.aotu.ai/t/how-to-run-the-official-website-capsule-on-the-client/50/7 "2020-04-14T17:09:27Z")
Oh, my mistake, this is a different problem than I originally though. Each Capsule is capable of receiving input from other capsules. If you go to our [the capsules section on our Downloads page](https://aotu.ai/docs/downloads/#capsules) page you can see the **Required Input** for each Capsule. For example, here are the required inputs for the capsules you currently have loaded: * * * This capsule requires any of the following detections: Vehicle, Bus, Car, Motorcycle, or Truck. It doesn’t need all of them, but at least one of them. ![image](https://us1.discourse-cdn.com/flex019/uploads/aotu/original/1X/61b4a198c82a611ee4ac2a043c1b347c1b06841d.png) This capsule requires a detection of type “Person” ![image](https://us1.discourse-cdn.com/flex019/uploads/aotu/original/1X/741abeacf7169a21a0af5ae2d151700c6e8e186f.png) Both of these (vehicles, persons) can be detected by our [Detector People And Vehicles Fast](https://aotu.ai/releases/brainframe/v0.24.0/detector_people_and_vehicles_fast.cap). Simple download this plugin, and the “Classifier Behavior Closeup” and “Classifier Vehicle Color” will work! ![image](https://us1.discourse-cdn.com/flex019/uploads/aotu/original/1X/d735bc96053870ffab15aaa5a47de7ee012c2c02.png) * * * This requires a detection of type “Face” ![image](https://us1.discourse-cdn.com/flex019/uploads/aotu/original/1X/aef680b13913a301979469ae2a0a25c068d11b84.png) This can be detected by several of our capsules. I recomend the [Detector Face Openvino](https://aotu.ai/releases/brainframe/v0.24.0/detector_face_openvino.cap) which runs quickly without a GPU, or [Detector Face Fast](https://aotu.ai/releases/brainframe/v0.24.0/detector_face_fast.cap) which runs quickly with a GPU. ![image](https://us1.discourse-cdn.com/flex019/uploads/aotu/original/1X/4052f2cc88aea2f38e95d87b6f53fa5b0284e9bc.png) ---
**Author:** ![shao](https://avatars.discourse-cdn.com/v4/letter/s/aeb1de/32.png) [@shao](https://forum.aotu.ai/u/shao)\ **Post date:** [April 15, 2020, 1:33am UTC](https://forum.aotu.ai/t/how-to-run-the-official-website-capsule-on-the-client/50/8 "2020-04-15T01:33:03Z")
Thank you very much for your help. It’s ready to run now！