content-agents

Start one NVIDIA Content Agents REST service locally with Docker Compose. Use when the user asks for /quickstart, local POC setup, or single-service Material, Physics, and Texture startup.

Manage Brev instances safely from the Brev CLI. Use when a workflow needs to list, create, access, copy to, execute on, port-forward, stop, or delete Brev instances for Content Agents dependency endpoints.

Deploy the full Content Agents package with a provider-neutral, endpoint-driven, multi-instance strategy. Use when the user asks to deploy all content agents, deploy material/physics/texture together, configure shared OVRTX rendering, choose VLM/LLM/image-gen/embedding endpoints, test the full package, or use Brev as an optional self-hosted dependency provider.

Deploy or smoke-test a Brev-hosted NVIDIA embedding NIM endpoint for Content Agents. Use when the user asks to deploy embeddings on Brev, host the llama-nemotron-embed-vl model, enable Material Agent prim clustering embeddings, test embedding sidecars, or create a Brev embedding endpoint for the collection deployment.

Deploy or smoke-test a Brev-hosted FLUX image-generation NIM endpoint for Content Agents. Use when the user asks to deploy image generation on Brev, host FLUX.2 Klein for Texture Agent, enable image-gen sidecars, test image-gen endpoints, or create a Brev image-gen endpoint for the collection deployment.

Deploy or smoke-test the Material Agent with Brev-hosted dependency endpoints. Use when the user asks to test material agent on Brev, deploy material agent with Brev, use RTX/L40S for rendering and A100/H100-grade GPU for VLM, run a Brev hybrid material-agent test, or recreate the Brev material-agent deployment. This workflow keeps the main pipeline local and uses Brev port-forwards to reach OVRTX and Qwen-family VLM endpoints.

Deploy the material-agent-service locally using Docker Compose with OVRTX rendering. Use when user wants to run material agent with docker, docker compose, set up local deployment, run the service locally with GPU rendering, start material agent containers, or configure VLM provider for docker deployment. Trigger phrases include "docker compose", "docker deploy", "run locally with docker", "start material agent docker", "docker up", "local deployment", "compose up".

Deploy just the OVRTX rendering API standalone via Docker Compose so one or more agent CLIs / services can point at it as a shared rendering endpoint. Use when user wants to run OVRTX standalone, deploy a shared rendering service, separate the rendering endpoint from an agent service, expose OVRTX to multiple callers, or set RENDER_ENDPOINT to a dedicated render host. Trigger phrases include "deploy ovrtx", "run ovrtx standalone", "shared rendering service", "ovrtx rendering docker", "render endpoint deploy", "ovrtx docker compose", "standalone rendering".

Deploy or smoke-test the Physics Agent with Brev-hosted dependency endpoints. Use when the user asks to test physics agent on Brev, deploy physics agent with Brev, use RTX/L40S for rendering and A100/H100-grade GPU for VLM, run a Brev hybrid physics-agent test, or recreate the Brev physics-agent deployment. This workflow keeps the main pipeline local and uses Brev port-forwards to reach OVRTX and Qwen-family VLM endpoints.

Deploy the physics-agent-service locally using Docker Compose with the bundled OVRTX GPU rendering sidecar. Use when user wants to run physics agent with docker, docker compose, set up local deployment of the physics service, run it on a GPU box, start physics agent containers, or configure the VLM provider for physics docker deployment. Trigger phrases include "deploy physics agent", "docker compose physics", "run physics agent locally", "start physics service docker", "physics compose up", "physics agent docker".

Deploy or smoke-test a Brev-hosted OpenAI-compatible Qwen VLM/LLM endpoint. Use when the user asks to deploy VLM on Brev, host Qwen on A100/H100, create a Qwen VLM endpoint for Material or Physics Agent, test a Brev model node, or recreate the validated Denvr A100 or Hyperstack H100 Qwen deployment. This workflow uses a local port-forward so local agent pipelines can call the remote endpoint.

Deploy or smoke-test the Texture Agent with Brev-hosted endpoints. Use when the user asks to test texture agent on Brev, deploy texture agent with Brev, run a Brev texture-agent service-only or hybrid test, host a small Qwen-family LLM for Texture Agent, or recreate the Brev texture-agent deployment. Texture Agent does not need OVRTX rendering by default.

Deploy the texture-agent-service locally using Docker Compose, with an optional FLUX.2 NIM image-gen sidecar. Use when user wants to run texture agent with docker, docker compose, set up local deployment, run the service locally, start texture agent containers, or route image generation to a locally-hosted NIM. Trigger phrases include "docker compose texture", "docker deploy texture", "run texture agent locally", "start texture agent docker", "texture agent up", "local texture deployment", "image-gen sidecar".

Flatten a composed USD stage into a single self-contained USD layer using the wu CLI. Use when the user wants to flatten a USD file, resolve sublayers, references, payloads, and inherits, merge USD composition into one file, or prepare a scene for sharing or rendering.

Generate images from text prompts using the wu CLI. Use when the user wants text-to-image generation, image-conditioned generation, visual material references, prompt-based concept images, or a local OpenAI-compatible image-generation endpoint through Gemini, OpenAI, or NVIDIA NIM backends.

Run the Material Agent CLI for VLM-based material assignment to 3D objects. Use when the user wants to run the material-agent CLI directly, assign materials to a USD file, run or resume the material pipeline, benchmark material predictions, build datasets from USD files, apply predicted materials, configure a material run, or try a SimReady demo.

Make requests to the Material Agent REST API service for VLM-based material assignment to 3D objects. Use when the user wants to use the Material Agent client, call the material agent service API, upload a USD file to the service, start or monitor a REST pipeline, generate reference images, download materialized results, or write a client script.

Run the Physics Agent CLI for VLM-based physics property classification of 3D assets. Use when the user wants to run the physics-agent CLI directly, classify asset components, identify asset type, build datasets from USD files, predict component material/type/physics properties, or author simulation-ready USD physics schemas.

Make requests to the Physics Agent REST API service for VLM-based physics and component classification of 3D USD assets. Use when the user wants to call the Physics Agent service API, upload or reference a USD file, run the REST classification pipeline, use prediction-only or tuning routes, monitor status, download predictions or simulation-ready USD, or write a client script.

Inspect and print USD scene hierarchy using the wu CLI. Use when the user wants to examine a USD file structure, list prims, show prim types, variants, API schemas, collections, custom token attributes, query a specific prim, limit traversal depth, or get scene statistics for .usd/.usda/.usdc/.usdz files.

Render USD files using the wu CLI with a configured remote rendering service. Use when the user wants to render a USD scene, generate images from .usd/.usda/.usdc/.usdz files, render all cameras or frame ranges, produce depth or segmentation sensors, focus or isolate prims, or test a render endpoint.

Run the Texture Agent CLI for AI-driven texture generation on USD materials. Use when the user wants to run the texture-agent CLI directly, add textures to a materialized USD asset, generate weathering or aging effects, run the texture pipeline, apply textures per material or per prim, or create texture variations.

Make requests to the Texture Agent REST API service for AI-driven texture generation on materialized USD assets. Use when the user wants to call the Texture Agent service API, upload a materialized USD, start or monitor a texture pipeline, control per-material texture prompts, download generated textures or USDZ output, or write a client script.

Run the Validation Agent Research Preview CLI for config-driven or prompt-driven validation of generated 3D content. Use when the user asks for validation-agent, run validation agent, validate asset, validate generated USD/image/video evidence, look_right, physics_sane, physical_behavior, render_valid, release validation checks, or Validation Agent V1 CLI artifacts.

Analyze images using a Vision-Language Model through the wu CLI. Use when the user wants to describe an image, caption a picture, ask questions about visual content, inspect renders or screenshots, compare visual evidence, or produce text or JSON answers with public VLM backends.