> This page is for version 3.3.0 (default).
> For other versions, use one of these documentation indexes:
> - 3.3.0 (default): https://docs.nvidia.com/vss/3.3.0/llms.txt
> - Dev: https://docs.nvidia.com/vss/dev/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/vss/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/vss/_mcp/server.

# VSS Agents

Agents built using VSS are AI-powered agents that can perform workflows such as video search, summarization, and reporting through leveraging vision-based tools.

## Deployment Architecture

The VSS Agents are deployed along with the 2D Vision AI with Agents Profile.

![2D Vision AI with Agents Profile](/vss/_fern-img/a929a78493d7d96ea73108f2fc024f260a13abcdd9906421d2ca3f94e666f77e.webp)

Above shows Agents deployed with the 2D Vision AI with Agents Profile.

## Components

* **LLM** ([Nemotron-3.5-Lightning-30B-A3B](https://build.nvidia.com/nvidia/nemotron-3.5-lightning-30b-a3b)): Reasoning and report generation
* **VLM** ([Cosmos3 Nano Reasoner](https://build.nvidia.com/nvidia/cosmos3-nano-reasoner)): Video understanding
* **VSS Agent**: Orchestrates LLM/VLM to process events and generate reports
* **Reference UI**: Browser-based chat interface for agent conversations