NVIDIA AI Blueprint for Video Search and Summarization (VSS) is a reference architecture for applications that use AI to search, analyze, question, and summarize live or recorded video. It is intended for building video analytics agents with vision-language models, language models, retrieval-augmented generation, and NVIDIA NIM microservices. The catalogue entries provide coding-agent rules, skills, commands, agents, instructions, and settings associated with the project.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarizationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/nvidia-ai-blueprints/video-search-and-summarization/ui-dev-server)<a href="https://agentmods.dev/commands/nvidia-ai-blueprints/video-search-and-summarization/ui-dev-server"><img src="https://agentmods.dev/badge/commands/nvidia-ai-blueprints/video-search-and-summarization/ui-dev-server/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/nvidia-ai-blueprints/video-search-and-summarization/ui-dev-server"><img src="https://agentmods.dev/badge/commands/nvidia-ai-blueprints/video-search-and-summarization/ui-dev-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00017 | $0.00854 |
| Opus 5.5 | $0.00007 | $0.00342 |
| Sonnet 5.5 | $0.00003 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
ui-dev-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
Start the VST UI dev server pointed at a backend host.
The UI project lives at ui/vios-ui/ (package vst-ui-ts) relative to the services/vios tree. All npm commands below must run from that directory — cd into it first. Do not assume the session working directory is the UI project root.
Arguments provided: $ARGUMENTS
Steps
1. Determine the backend URL
- If
$ARGUMENTSis non-empty, parse it as<ip:port>with an optional trailing path. - If no arguments were given, use
AskUserQuestionto ask the user:- "What is the backend IP and port? (e.g. :30888)"
- Default path is
/vstif none provided. - Construct the full URL:
http://<ip>:<port><path>
2. Edit ui/vios-ui/src/config.tsx
Read the file first, then apply one of the two cases below:
Case A — file is in original (unedited) state:
Detect by presence of isDevelopment or getPort function definitions.
Replace this entire block (from after the import line to before export default):
const isDevelopment = () => {
return process.env.NODE_ENV === 'development';
};
const getPort = () => {
return isDevelopment() ? '30000' : window.location.port;
};
const mdatWebAPIDefaultPort = '8081';
const analyticsUIServerDefaultPort = '8003';
const config: Config = {
sensorManagementEndpoint: `${window.location.protocol}//${window.location.hostname}:${getPort()}`,
streamRecorderEndpoint: `${window.location.protocol}//${window.location.hostname}:${getPort()}`,
storageManagementEndpoint: `${window.location.protocol}//${window.location.hostname}:${getPort()}`,
liveStreamEndpoint: `${window.location.protocol}//${window.location.hostname}:${getPort()}`,
replayStreamEndpoint: `${window.location.protocol}//${window.location.hostname}:${getPort()}`,
streambridgeEndpoint: `${window.location.protocol}//${window.location.hostname}:${getPort()}`,
mdatWebApiEndpoint: `${window.location.protocol}//${window.location.hostname}:${mdatWebAPIDefaultPort}`,
analyticsUIServerEndpoint: `${window.location.protocol}//${window.location.hostname}:${analyticsUIServerDefaultPort}`,
enableLogs: true, // enable-disable console logs
};
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +14 lines 0a225ae85dc5
- 1mo ago First seen · 103 lines · 17 tokens per session scan A ac3bab7eace1
ui-dev-server is a command published in the GitHub repository NVIDIA-AI-Blueprints/video-search-and-summarization (1,947 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 854 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
generate-embeddings
Generate vector embeddings for text data using embedding models.
search-similar
Find semantically similar items using vector similarity search.
doctor
Diagnose the bubbaloop install end-to-end — token, daemon, MCP transport, Zenoh router, mode, registered nodes — and tell the user the precise fix for any red status.
node-validate
Validate a node's manifest, directory structure, and command schema against the bubbaloop contract.
stream
Get the Zenoh topic and connection params for a node's data stream.
node-new
Scaffold a new bubbaloop node via the bubbaloop-node-author subagent — guided through manifest, command queryable, validation, and registration.