> For the complete documentation index, see [llms.txt](https://openvision-2.gitbook.io/whitepaper/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://openvision-2.gitbook.io/whitepaper/core-architecture/visionnode.md).

# VisionNode

Chrome + Desktop App + cameras

<figure><img src="https://87869382-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FEEwhqHtUOYy7RtuwH7O9%2Fuploads%2FKHMCQT0Hy1a6Jcmy61at%2FVisionNode.jpg?alt=media&amp;token=83bb73f0-840f-465f-a370-63000b24e93a" alt=""><figcaption></figcaption></figure>

* Converts user PCs into training or inference nodes or bandwidth
* Uploads video data and streams (e.g., dashcams, CCTV)
* Benchmarks GPU/RAM/Uptime and matches training tasks
* Supports both inference jobs and fine-tuning workloads, depending on contributor
  \
  specs