> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/vss/dev/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/vss/_mcp/server. # Dev ## Docs - [Release Notes](https://docs.nvidia.com/vss/dev/release-notes.md): - [Getting Started](https://docs.nvidia.com/vss/dev/getting-started.md): - [Prerequisites](https://docs.nvidia.com/vss/dev/getting-started/prerequisites.md): - [Quickstart](https://docs.nvidia.com/vss/dev/getting-started/quickstart.md): - [Agent Workflows](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows.md): - [Video Summarization](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/video-summarization.md): - [Search](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/search.md): - [Alert Verification](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/alert-verification.md): - [Real-Time Alerts](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/real-time-alerts.md): - [Industry-Specific Examples](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples.md): - [Smart City Blueprint](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint.md): - [Introduction to the NVIDIA Smart City AI Blueprint](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/introduction-to-the-nvidia-smart-city-ai-blueprint.md): - [Prerequisites](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/prerequisites.md): - [Quickstart Guide - Docker Compose](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/quickstart-guide-docker-compose.md): - [Development Workflow](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/development-workflow.md): - [Blueprint Deep Dive](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/development-workflow/blueprint-deep-dive.md): - [Calibration](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/development-workflow/calibration.md): - [Deployment](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/development-workflow/deployment.md): - [Simulation and Synthetic Data Generation](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/development-workflow/simulation-and-synthetic-data-generation.md): - [Model Fine Tuning](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/development-workflow/model-fine-tuning.md): - [Operations (Monitoring, Troubleshooting, FAQ, Known Limitations)](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/operations-monitoring-troubleshooting-faq-known-limitations.md): - [Known Limitations](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/operations-monitoring-troubleshooting-faq-known-limitations/known-limitations.md): - [Troubleshooting Guide](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/operations-monitoring-troubleshooting-faq-known-limitations/troubleshooting-guide.md): - [FAQ](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/operations-monitoring-troubleshooting-faq-known-limitations/faq.md): - [License Information](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint/operations-monitoring-troubleshooting-faq-known-limitations/license-information.md): - [Warehouse Operations Blueprint](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint.md): - [Introduction](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/introduction.md): - [Release Notes](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/release-notes.md): - [Prerequisites](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/prerequisites.md): - [Quickstart](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/quickstart.md): - [Helm Deployment](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/helm-deployment.md): - [Development Workflow](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow.md): - [Deployment & Customization](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/deployment-customization.md): - [2D Vision AI Profile](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/deployment-customization/2d-vision-ai-profile.md): - [2D Vision AI with Agents Profile](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/deployment-customization/2d-vision-ai-with-agents-profile.md): - [3D Vision AI Profile](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/deployment-customization/3d-vision-ai-profile.md): - [MV3DT Vision AI Profile](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/deployment-customization/mv3dt-vision-ai-profile.md): - [Simulation and Synthetic Data Generation](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation.md): - [Development Tools Setup](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation/development-tools-setup.md): - [Synthetic Data Generation](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation/synthetic-data-generation.md): - [Quick Start for SDG](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation/synthetic-data-generation/quick-start-for-sdg.md): - [Camera Calibration](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation/synthetic-data-generation/camera-calibration.md): - [Scene Customization](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation/scene-customization.md): - [NavMesh Setup](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation/scene-customization/navmesh-setup.md): - [Camera Placement](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation/scene-customization/camera-placement.md): - [Semantic Label Setup](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation/scene-customization/semantic-label-setup.md): - [Customized Scene Saving](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation/scene-customization/customized-scene-saving.md): - [Dataset Post-Processing](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation/dataset-post-processing.md): - [Sim2Real Data Transfer](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/simulation-and-synthetic-data-generation/sim2real-data-transfer.md): - [Model Finetuning](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/model-finetuning.md): - [RT-DETR (2D warehouse detection)](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/model-finetuning/rt-detr.md): - [Sparse4D (3D multi-camera)](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/model-finetuning/sparse4d.md): - [Cosmos Reasoner](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/development-workflow/model-finetuning/cosmos-reasoner.md): - [Microservice Configuration](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/microservice-configuration.md): Configuration and outputs of microservices used in the Warehouse Operations Blueprint. - [Perception](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/microservice-configuration/perception.md): - [2D Single Camera Detection and Tracking (RT-DETR)](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/microservice-configuration/perception/2d-single-camera-detection-and-tracking-rt-detr.md): - [3D Multi Camera Detection and Tracking (Sparse4D)](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/microservice-configuration/perception/3d-multi-camera-detection-and-tracking-sparse4d.md): - [3D Multi Camera Detection and Tracking (MV3DT)](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/microservice-configuration/perception/3d-multi-camera-detection-and-tracking-mv3dt.md): - [Behavior Analytics](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/microservice-configuration/behavior-analytics.md): - [VSS Configurator](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/microservice-configuration/vss-configurator.md): Warehouse blueprint configuration flow, profile inputs, file changes, and runtime sensor behavior. - [Alerting Service](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/microservice-configuration/alerting-service.md): - [Agents](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/microservice-configuration/agents.md): - [Reference Agentic UI](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/microservice-configuration/reference-agentic-ui.md): - [Operations (Monitoring, Troubleshooting, FAQ, Known Limitations)](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/operations-monitoring-troubleshooting-faq-known-limitations.md): - [Accuracy & Performance Benchmarks](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/operations-monitoring-troubleshooting-faq-known-limitations/accuracy-performance-benchmarks.md): - [System Sizing Guide](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/operations-monitoring-troubleshooting-faq-known-limitations/system-sizing-guide.md): - [Known Limitations](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/operations-monitoring-troubleshooting-faq-known-limitations/known-limitations.md): - [Troubleshooting Guide](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/operations-monitoring-troubleshooting-faq-known-limitations/troubleshooting-guide.md): - [FAQ](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/operations-monitoring-troubleshooting-faq-known-limitations/faq.md): - [License Information](https://docs.nvidia.com/vss/dev/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint/operations-monitoring-troubleshooting-faq-known-limitations/license-information.md): - [Agent Skills](https://docs.nvidia.com/vss/dev/vision-agent/agent-skills.md): - [Build Vision AI Skill](https://docs.nvidia.com/vss/dev/vision-agent/build-vision-ai.md): - [Agent Harnesses](https://docs.nvidia.com/vss/dev/vision-agent/agent-harnesses.md): - [NemoClaw](https://docs.nvidia.com/vss/dev/vision-agent/agent-harnesses/nemoclaw.md): - [Setup VSS and Skills](https://docs.nvidia.com/vss/dev/vision-agent/agent-harnesses/nemoclaw/setup-vss-and-skills.md): - [VSS Orchestrator MCP](https://docs.nvidia.com/vss/dev/vision-agent/agent-harnesses/nemoclaw/vss-orchestrator-mcp.md): - [Additional Configuration](https://docs.nvidia.com/vss/dev/vision-agent/agent-harnesses/nemoclaw/additional-configuration.md): - [Troubleshooting](https://docs.nvidia.com/vss/dev/vision-agent/agent-harnesses/nemoclaw/troubleshooting.md): - [VSS Agents](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents.md): - [Agent Overview](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/agent-overview.md): - [API Reference](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/agent-overview/api-reference.md): REST endpoints for the VSS Agent FastAPI front end. - [Agent Profiles](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/agent-profiles.md): - [Agent Configuration](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/agent-configuration.md): Reference for VSS Agent YAML and environment configuration - [Agent Customization](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/agent-customization.md): - [Configure the LLM](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/agent-customization/customize-models/configure-the-llm.md): - [Configure the VLM](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/agent-customization/customize-models/configure-the-vlm.md): - [Agent Evaluation](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/agent-evaluation.md): - [Report Generation](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/report-generation.md): - [Observability](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/observability.md): - [Video-Analytics-MCP Server](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/video-analytics-mcp-server.md): - [Agent Known Issues](https://docs.nvidia.com/vss/dev/vision-agent/vss-agents/agent-known-issues.md): - [Vision Microservices](https://docs.nvidia.com/vss/dev/system-components/vision-microservices.md): - [Object Detection and Tracking](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/object-detection-and-tracking.md): - [API Reference](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/object-detection-and-tracking/api-reference.md): REST endpoints for the Real Time Video Intelligence CV (RTVI-CV) microservice. - [MV3DT Standalone Deployment](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/object-detection-and-tracking/mv3dt-standalone-deployment.md): Deploy RT-CV-3D standalone: RT-DETR detection with Multi-View 3D Tracking (MV3DT) and BEV fusion, using Docker Compose. - [Real-Time VLM](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/real-time-vlm.md): - [API Reference](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/real-time-vlm/api-reference.md): - [Video Embedding Generation](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/video-embedding-generation.md): - [API Reference](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/video-embedding-generation/api-reference.md): REST endpoints for the Real-Time Embedding microservice. - [Video Summarization](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/video-summarization.md): - [API Reference](https://docs.nvidia.com/vss/dev/system-components/vision-microservices/video-summarization/api-reference.md): - [Analytics Microservices](https://docs.nvidia.com/vss/dev/system-components/analytics-microservices.md): - [Behavior Analytics](https://docs.nvidia.com/vss/dev/system-components/analytics-microservices/behavior-analytics.md): - [Alerts Microservice](https://docs.nvidia.com/vss/dev/system-components/analytics-microservices/alerts-microservice.md): - [Alert Verification API](https://docs.nvidia.com/vss/dev/system-components/analytics-microservices/alerts-microservice/alert-verification-api.md): - [Middleware](https://docs.nvidia.com/vss/dev/system-components/middleware.md): - [Video IO & Storage (VIOS)](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios.md): - [VIOS Microservices](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vios-microservices.md): - [NVStreamer](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/nvstreamer.md): - [VST API Reference](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference.md): - [VST Sensor Management API](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-sensor-management-api.md): - [VST Sensor Management API Reference](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-sensor-management-api/vst-sensor-management-api-reference.md): The Sensor Management Service is a comprehensive system designed to facilitate the administration and control of sensor-related functionalities. It streamlines sensor operations, - [VST Live Stream Management API](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-live-stream-management-api.md): - [VST Live Stream Management API Reference](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-live-stream-management-api/vst-live-stream-management-api-reference.md): The Live Stream Service is designed to facilitate the live or real time streaming of sensors. This service encompasses: - Live streaming: Live streaming of sensors using WebRTC pr - [VST Replay Stream Management API](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-replay-stream-management-api.md): - [VST Replay Stream Management API Reference](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-replay-stream-management-api/vst-replay-stream-management-api-reference.md): The Replay Stream Service supports recorded sensor streaming using WebRTC, listing recorded streams, capturing snapshots, monitoring stream status in real time, playback controls (fast forward, rewind, seeking, play, and pause), performance statistics, and queries for stream position and metadata. - [VST Record Stream Management API](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-record-stream-management-api.md): - [VST Record Stream Management API Reference](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-record-stream-management-api/vst-record-stream-management-api-reference.md): VST Stream Recorder MS is used to manage recording of sensors NOTE: All JSON responses from this service are emitted with HTTP header `Content-Type: text/plain`. The body itself is - [VST Proxy Stream Management API](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-proxy-stream-management-api.md): - [VST Proxy Stream Management API Reference](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-proxy-stream-management-api/vst-proxy-stream-management-api-reference.md): VST Replay Stream MS is used to manage proxy RTSP URLs sensors NOTE: All JSON responses from this service are emitted with HTTP header `Content-Type: text/plain`. The body itself i - [VST Storage Management API](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-storage-management-api.md): - [VST Storage Management API Reference](https://docs.nvidia.com/vss/dev/system-components/middleware/video-io-storage-vios/vst-api-reference/vst-storage-management-api/vst-storage-management-api-reference.md): The Storage Management is designed to facilitate the management of media files. For nvstreamer the media files are static media files that are scanned from the specified directory - [API Gateway / MCP](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp.md): - [Video Analytics API](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api.md): - [Video Analytics API Reference](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference.md): Request and response schemas for the Video Analytics API - [Video Analytics MCP](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-mcp.md): - [Message Broker](https://docs.nvidia.com/vss/dev/system-components/middleware/message-broker.md): - [Kafka](https://docs.nvidia.com/vss/dev/system-components/middleware/message-broker/kafka.md): - [Redis](https://docs.nvidia.com/vss/dev/system-components/middleware/message-broker/redis.md): - [NvSchema](https://docs.nvidia.com/vss/dev/system-components/middleware/nvschema.md): - [JSON Schema](https://docs.nvidia.com/vss/dev/system-components/middleware/nvschema/json-schema.md): - [Protobuf Schema](https://docs.nvidia.com/vss/dev/system-components/middleware/nvschema/protobuf-schema.md): - [Database](https://docs.nvidia.com/vss/dev/system-components/middleware/database.md): - [ELK](https://docs.nvidia.com/vss/dev/system-components/middleware/database/elk.md): - [Observability](https://docs.nvidia.com/vss/dev/system-components/middleware/observability.md): - [User Interface](https://docs.nvidia.com/vss/dev/system-components/user-interface.md): - [Models](https://docs.nvidia.com/vss/dev/system-components/models.md): - [Model customization overview](https://docs.nvidia.com/vss/dev/system-components/models/model-customization-overview.md): - [SigLIP 2 object embeddings](https://docs.nvidia.com/vss/dev/system-components/models/siglip-2-object-embeddings.md): - [Cosmos-Embed1 (video embedding)](https://docs.nvidia.com/vss/dev/system-components/models/cosmos-embed1-video-embedding.md): - [Sparse4D (3D multi-camera)](https://docs.nvidia.com/vss/dev/system-components/models/sparse4d-3d-multi-camera.md): - [RT-DETR (2D warehouse detection)](https://docs.nvidia.com/vss/dev/system-components/models/rt-detr-2d-warehouse-detection.md): - [Configuration](https://docs.nvidia.com/vss/dev/system-components/configuration.md): Environment-variable reference for VSS developer-profile deployments - [VSS Configurator](https://docs.nvidia.com/vss/dev/system-components/configuration/vss-configurator.md): - [SDR Controller](https://docs.nvidia.com/vss/dev/system-components/configuration/sdr-controller.md): - [Deepstream Configurator](https://docs.nvidia.com/vss/dev/system-components/configuration/deepstream-configurator.md): - [VLM Autoscaling](https://docs.nvidia.com/vss/dev/system-components/configuration/vlm-autoscaling.md): - [Calibration](https://docs.nvidia.com/vss/dev/system-components/calibration.md): - [Auto Calibration](https://docs.nvidia.com/vss/dev/system-components/calibration/auto-calibration.md): - [Getting Started](https://docs.nvidia.com/vss/dev/system-components/calibration/auto-calibration/getting-started.md): - [Workflow Steps](https://docs.nvidia.com/vss/dev/system-components/calibration/auto-calibration/workflow-steps.md): - [Custom Dataset](https://docs.nvidia.com/vss/dev/system-components/calibration/auto-calibration/custom-dataset.md): - [Troubleshooting](https://docs.nvidia.com/vss/dev/system-components/calibration/auto-calibration/troubleshooting.md): - [SDG Calibration](https://docs.nvidia.com/vss/dev/system-components/calibration/sdg-calibration.md): - [Legacy Camera Calibration](https://docs.nvidia.com/vss/dev/system-components/calibration/legacy-camera-calibration.md): - [Camera Positioning Guide](https://docs.nvidia.com/vss/dev/system-components/calibration/camera-positioning-guide.md): - [Calibration Schema](https://docs.nvidia.com/vss/dev/system-components/calibration/calibration-schema.md): - [API Reference](https://docs.nvidia.com/vss/dev/appendix/api-reference.md): - [Performance](https://docs.nvidia.com/vss/dev/appendix/performance.md): - [Alert Verification Performance](https://docs.nvidia.com/vss/dev/appendix/performance/agent-workflows/alert-verification-performance.md): - [Video Summarization Performance](https://docs.nvidia.com/vss/dev/appendix/performance/agent-workflows/video-summarization-performance.md): - [Search Performance](https://docs.nvidia.com/vss/dev/appendix/performance/agent-workflows/search-performance.md): - [RT-CV Performance](https://docs.nvidia.com/vss/dev/appendix/performance/microservices/rt-cv-performance.md): - [RT-VLM Performance](https://docs.nvidia.com/vss/dev/appendix/performance/microservices/rt-vlm-performance.md): - [RT-Embed Performance](https://docs.nvidia.com/vss/dev/appendix/performance/microservices/rt-embed-performance.md): - [VIOS Performance](https://docs.nvidia.com/vss/dev/appendix/performance/microservices/vios-performance.md): - [Additional Deployments](https://docs.nvidia.com/vss/dev/appendix/additional-deployments.md): - [Brev Launchable](https://docs.nvidia.com/vss/dev/appendix/additional-deployments/brev-launchable.md): - [Edge Deployment](https://docs.nvidia.com/vss/dev/appendix/additional-deployments/edge-deployment.md): - [Helm Deployment](https://docs.nvidia.com/vss/dev/appendix/additional-deployments/helm-deployment.md): - [Secure Deployment](https://docs.nvidia.com/vss/dev/appendix/additional-deployments/secure-deployment.md): - [FAQ](https://docs.nvidia.com/vss/dev/appendix/faq.md): - [Known Limitations](https://docs.nvidia.com/vss/dev/appendix/known-limitations.md): - [License Information](https://docs.nvidia.com/vss/dev/appendix/license-information.md): - [EULA](https://docs.nvidia.com/vss/dev/appendix/eula.md): ## API Docs - Video Analytics API Reference > metrics [Get average speed](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-average-speed.md) - Video Analytics API Reference > metrics [Get flow rate](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-flowrate.md) - Video Analytics API Reference > metrics [Get average speed and flow rate](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-average-speed-with-flowrate.md) - Video Analytics API Reference > metrics [Get average speed and travel time](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-average-speed-with-travel-time.md) - Video Analytics API Reference > metrics [Get tripwire counts](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-tripwire-counts.md) - Video Analytics API Reference > metrics [Get tripwire-based occupancy](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-tripwire-based-occupancy.md) - Video Analytics API Reference > metrics [Reset place occupancy](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-reset-occupancy.md) - Video Analytics API Reference > metrics [Get tripwire count histogram](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-tripwire-histogram.md) - Video Analytics API Reference > metrics [Get FOV occupancy](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-fov-occupancy.md) - Video Analytics API Reference > metrics [Get FOV occupancy histogram](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-fov-histogram.md) - Video Analytics API Reference > metrics [Get ROI occupancy](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-roi-occupancy.md) - Video Analytics API Reference > metrics [Get ROI occupancy histogram](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-roi-histogram.md) - Video Analytics API Reference > metrics [Get mutually exclusive ROI occupancy](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-occupancy-based-on-mutually-exclusive-roi.md) - Video Analytics API Reference > metrics [Get tracker-based occupancy](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-occupancy-tracker.md) - Video Analytics API Reference > metrics [Get tracker occupancy histogram](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-tripwire-occupancy-histogram.md) - Video Analytics API Reference > metrics [Get space utilization histogram](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-space-utilization-histogram.md) - Video Analytics API Reference > metrics [Get last processed timestamp](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-metrics-get-last-processed-timestamp.md) - Video Analytics API Reference > metrics [Get road-segment speeds](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/metrics/controller-road-network-average-segment-speed.md) - Video Analytics API Reference > tracker [Get unique object count](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/tracker/controller-tracker-get-unique-object-count.md) - Video Analytics API Reference > tracker [Get unique object count and locations](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/tracker/controller-tracker-get-unique-object-count-with-locations.md) - Video Analytics API Reference > tracker [Get tracked objects](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/tracker/controller-tracker-get-unique-objects.md) - Video Analytics API Reference > tracker [Get behavior locations](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/tracker/controller-tracker-get-behavior-locations.md) - Video Analytics API Reference > tracker [Get the latest RTLS or AMR record](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/tracker/controller-tracker-get-last-record.md) - Video Analytics API Reference > frames [Get raw frame metadata](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/frames/controller-frames-get-raw-frames.md) - Video Analytics API Reference > frames [Get enhanced frame metadata](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/frames/controller-frames-get-enhanced-frames.md) - Video Analytics API Reference > frames [Get BEV frame metadata](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/frames/controller-frames-get-bev-frames.md) - Video Analytics API Reference > frames [Get frame-based alerts](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/frames/controller-frames-get-alerts.md) - Video Analytics API Reference > frames [Get high-confidence frame objects](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/frames/controller-frames-get-high-confidence-objects.md) - Video Analytics API Reference > frames [Get proximity clusters](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/frames/controller-frames-get-proximity-clusters.md) - Video Analytics API Reference > frames [Get frame PTS](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/frames/controller-frames-get-pts.md) - Video Analytics API Reference > behavior [Get behaviors](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/behavior/controller-behavior-get-behavior.md) - Video Analytics API Reference > behavior [Get behavior PTS](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/behavior/controller-behavior-get-pts.md) - Video Analytics API Reference > alerts [Get alerts](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/alerts/controller-alerts-get-alerts.md) - Video Analytics API Reference > alerts [Get severe alerts by place or sensor](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/alerts/controller-alerts-get-severe-alerts.md) - Video Analytics API Reference > incidents [Get incidents](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/incidents/controller-incidents-get-incidents.md) - Video Analytics API Reference > incidents [Get severe incidents by place or sensor](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/incidents/controller-incidents-get-severe-incidents.md) - Video Analytics API Reference > clustering [Get behavior clusters](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/clustering/controller-clustering-get-clustering-results.md) - Video Analytics API Reference > clustering [Label a behavior cluster](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/clustering/controller-clustering-add-cluster-label.md) - Video Analytics API Reference > events [Get tripwire events](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/events/controller-events-get-tripwire-events.md) - Video Analytics API Reference > events [Get AMR events](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/events/controller-events-get-amr-events.md) - Video Analytics API Reference > events [Get ROI events](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/events/controller-events-get-roi-events.md) - Video Analytics API Reference > config [Upload a configuration file](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-upload-file.md) - Video Analytics API Reference > config [Update service configuration](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-update.md) - Video Analytics API Reference > config [Get configuration update status](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-get-update-status.md) - Video Analytics API Reference > config [Upsert sensor calibration](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-upsert-calibration.md) - Video Analytics API Reference > config [Delete sensor calibration](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-delete-sensor-calibration.md) - Video Analytics API Reference > config [Get calibration configuration](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-get-calibration-config.md) - Video Analytics API Reference > config [Get calibration modification timestamp](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-get-calibration-last-modified-timestamp.md) - Video Analytics API Reference > config [Get road-network configuration](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-get-road-network-config.md) - Video Analytics API Reference > config [Get USD asset configuration](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-get-usd-assets-config.md) - Video Analytics API Reference > config [Upload calibration images](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-upload-calibration-images.md) - Video Analytics API Reference > config [Get a calibration image](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-get-calibration-image.md) - Video Analytics API Reference > config [Get calibration image metadata](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-get-calibration-image-metadata.md) - Video Analytics API Reference > config [Delete calibration images](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/config/controller-config-delete-calibration-images.md) - Video Analytics API Reference > sensor [Find sensors covering a floor-plan coordinate](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/sensor/controller-sensor-get-sensor-lookup.md) - Video Analytics API Reference > livez [Check service health](https://docs.nvidia.com/vss/dev/system-components/middleware/api-gateway-mcp/video-analytics-api/video-analytics-api-reference/livez/controller-livez-is-alive.md) ## OpenAPI Specification The raw OpenAPI 3.1 specification for this API is available at: - [OpenAPI JSON](https://docs.nvidia.com/vss/openapi.json) - [OpenAPI YAML](https://docs.nvidia.com/vss/openapi.yaml) > **Note:** This page contains both a page directory (above) and the landing page content (below). The page directory is generated for agent use and does not appear on the landing page. > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/vss/dev/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/vss/_mcp/server. # Introduction The NVIDIA Blueprint for Video Search and Summarization (VSS) provides a suite of reference architectures for building vision agents and AI-powered video analytics applications. These reference architectures include accelerated vision-based microservices, VLMs, and LLMs which can be used in your existing applications, as standalone microservices, or as part of a larger vision agent built using the blueprint. > **Info** > > **Intended deployment environment:** Deploy VSS in a trusted, isolated network. > Do not expose the VSS services directly to untrusted networks. This release assumes > authentication, TLS termination, rate limiting, and external access controls > are provided by the infrastructure. For details, see > [Known Limitations](/appendix/known-limitations) and > [Secure Deployment](/appendix/additional-deployments/secure-deployment). ## Architecture Overview ![VSS High Level Architecture](/vss/_fern-img/e3a2810a613f30c365cd8ad42ca684fad69f222838e3d9e49ec4226044fba0de.webp) VSS is broken down into 3 major areas of video processing and analysis: 1. **Real-time video intelligence**: Extracts features from stored and streamed video in real-time, either continuously or on demand. 2. **Downstream analytics**: Analyzes extracted features posted to a message broker or stored in a database for downstream analysis. 3. **Agentic and offline processing**: Processes extracted features to generate reports, answers questions, and provides video search capabilities. ### Real-Time Video Intelligence The Real-Time Video Intelligence layer extracts rich visual features, semantic embeddings, and contextual understanding from video data in real-time, publishing results to a message broker for downstream analytics and agentic workflows. It provides three core microservices for processing video streams: * [Real-Time Computer Vision (RT-CV)](/system-components/vision-microservices/object-detection-and-tracking): leverages NVIDIA DeepStream SDK with models like RT-DETR, Grounding DINO, and Sparse4D to perform real-time object detection, classification, and multi-object tracking on single or multi-camera streams. * [Real-Time Embedding (RT-Embedding)](/system-components/vision-microservices/video-embedding-generation): generates semantic embeddings from video, images, and live RTSP streams using Cosmos-Embed1 models, enabling efficient video search and similarity matching. * [Real-Time VLM (RT-VLM)](/system-components/vision-microservices/real-time-vlm): applies Vision Language Models (such as Cosmos Reason1/2 and Qwen3-VL) to generate natural language captions, detect incidents, and identify anomalies in video streams. ### Downstream Analytics The Downstream Analytics layer processes and enriches the metadata streams generated by real-time video intelligence microservices, transforming raw detections into actionable insights and verified alerts. It provides two core microservices: * [Behavior Analytics](/system-components/analytics-microservices/behavior-analytics): consumes frame metadata from message brokers (Kafka, Redis Streams, or MQTT), tracks objects over time across camera sensors, and computes behavioral metrics including speed, direction, and trajectory. It detects spatial events (tripwire crossings, ROI entry/exit) and generates incidents based on configurable violation rules (proximity detection, restricted zones, confined areas). * [Alerts Microservice](/system-components/analytics-microservices/alerts-microservice): ingests alerts and incidents from upstream analytics or computer vision pipelines, retrieves corresponding video segments based on alert timestamps, and uses Vision Language Models to verify alert authenticity. Verified results with verdicts (confirmed/rejected/unverified) and reasoning traces are persisted to Elasticsearch and optionally published to Kafka for downstream consumption. ### Agent and Offline Processing The Agent and Offline Processing layer provides an agent that orchestrates vision-based tools to generate insights, reports, and search capabilities from video content. The [top-level agent](/vision-agent/vss-agents/agent-overview) leverages the Model Context Protocol (MCP) to access video analytics data, incident records, and vision processing capabilities through a unified tool interface. It integrates multiple vision-based tools including video understanding with Vision Language Models (VLMs), semantic video search using embeddings, video summarization for extended footage analysis, and video snapshot/clip retrieval. These tools can also be used as standalone microservices, independent of the agent. ## Why VSS? VSS is a reference architecture purpose-built for production vision agents. Compared to building a vision agent from scratch, assembling one from generic third-party agent frameworks, or stitching together cloud vision and video understanding APIs, VSS offers three core advantages: 1. **GPU-accelerated real-time video pipeline.** VSS uses the NVIDIA DeepStream SDK with TensorRT/Triton-accelerated models and streaming batched inference to process many concurrent camera streams on a single GPU. Throughput scales with available GPU resources rather than per-request API quotas, and capabilities such as synchronized multi-camera 3D detection and tracking with [Sparse4D](/system-components/models/sparse4d-3d-multi-camera) are not exposed by cloud-only vision APIs. See [Performance](/appendix/performance) for measured throughput per GPU. 2. **Modular, composable microservices with MCP-based orchestration.** Every capability in VSS - real-time computer vision, real-time VLM, embedding generation, behavior analytics, alert verification, summarization - is a standalone microservice with associated Agent Skills and documented REST and MCP interface. Developers deploy only the components they need, swap VLMs and LLMs (Cosmos Reason, Qwen3-VL, local NIMs, or remote model endpoints) without rebuilding services, and integrate the tools into any agent framework via the [API Gateway / MCP](/system-components/middleware/api-gateway-mcp) layer. This avoids both the SDK lock-in of cloud vendor stacks and the bespoke plumbing (message brokers, calibration, multi-stream orchestration, alert verification) required when assembling generic agent frameworks from scratch. 3. **On-premise and edge deployment with no cloud dependency.** Because VSS runs on NVIDIA NIMs and locally hosted models, the full pipeline - from video ingest through VLM reasoning - can run inside a trusted, isolated network with no data egress. Reference profiles cover datacenter GPUs, [edge devices such as DGX Spark, IGX Thor, and AGX Thor](/appendix/additional-deployments/edge-deployment), and [Helm-based Kubernetes](/appendix/additional-deployments/helm-deployment) clusters. For workloads with data sovereignty, latency, or cost-predictability constraints, this avoids the per-request pricing, region restrictions, and closed-source models that come with cloud vision APIs. ## Operating VSS with Agent Harnesses VSS ships with first-class support for driving the blueprint through natural-language coding agents and agent sandboxes, so developers do not need to memorize compose flags, REST payloads, or MCP tool signatures to deploy and operate the stack. ### Agent Skills [Agent Skills](/vision-agent/agent-skills) are reusable, self-contained capabilities that follow the [agentskills.io](https://agentskills.io) specification and package the prompts, reference data, and helper scripts a coding agent needs to operate a deployed VSS Blueprint. Each Skill maps a developer intent - *"deploy VSS for video search"*, *"add a camera"*, *"summarize this video"*, *"verify these alerts"* - onto the corresponding VSS REST, VA-MCP, and VIOS calls. Skills are versioned alongside the blueprint in the VSS repository, exercised by a CI eval workflow on every change, and consumed by any compatible coding agent (such as Claude Code or Codex) at either deployment time or runtime. ### Agent Harnesses An [agent harness](/vision-agent/agent-harnesses) is the coding agent or agent sandbox that loads the VSS Agent Skills and drives the blueprint. Because every Skill follows the [agentskills.io](https://agentskills.io) specification, any compatible harness can load the same Skills folder without bespoke integration code. Validated harnesses include CLI coding agents such as Claude Code and OpenAI Codex - used to stand up a VSS profile from a request like *"Deploy VSS for video search"* - and always-on agent sandboxes such as OpenClaw and NemoClaw, which load the same Skills and act as the operational chat interface to a running deployment. See [Agent Harnesses](/vision-agent/agent-harnesses) for the full list of supported harnesses, their Skills directories, and install flows. ## Deployment Types To demonstrate the use of the VSS architecture, we provide two deployment types: * **Developer Profiles**: Deployment type for developers to test and experiment with the VSS architecture. It starts with deploying a basic video agent and then builds on it with additional workflows. * **Blueprint Examples**: Deployment type for industry-specific use cases, demonstrating typical E2E deployments from video input to agentic workflows. ### Developer Profiles Developer profiles are docker compose deployments which demonstrate the assembly of various VSS microservices to fulfill specific agent workflows. They are designed to be a starting point for developers to test and experiment with the VSS architecture. To see the developer profiles and their respective workflows, see [agent-workflows](/vision-agent/agent-workflows). ### Industry-Specific Examples Industry-specific examples demonstrate the use of the VSS architecture in a variety of industry-specific use cases. These advanced reference deployments include parameters, sample data, and configurations which address key use cases. We provide two blueprint examples: * [Smart City Blueprint](/vision-agent/agent-workflows/industry-specific-examples/smart-city-blueprint): A blueprint example which leverages VSS for smart city use cases, including person and vehicle detection/tracking and event verification of collisions. * [Warehouse Operations Blueprint](/vision-agent/agent-workflows/industry-specific-examples/warehouse-operations-blueprint): A blueprint example which leverages VSS for warehouse operations use cases, including people and forklift detection/tracking and event verification of near-miss events.