Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Build a DeepStream video analytics pipeline v1.0.0

Use this resource to build a DeepStream video analytics pipeline with TensorRT inference and messaging

New

  • 355 downloads
  • 132 likes
  • 132 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install video-analytics-pipeline-deepstream

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent checks the references for the API, GStreamer plugins, nvinfer configuration and Kafka before writing code. It follows the memory rules and the SDK version requirements.

Mostly picked by

Updated November 2, 2026

Card for the “Build a DeepStream video analytics pipeline” skill

Details

Generates with
Your agent's model
Licence
CC-BY-4.0

Similar resources

View all

What you get

  • SKILL.md : architecture, rules and key paths
  • references/nvinfer_config.md : inference configuration
  • references/kafka_messaging.md : Kafka messaging

Good fit for

  • You detect and track objects in video streams
  • You send analytics results to Kafka

Not for

    Tags

    • deepstream
    • video
    • tensorrt
    • gstreamer
    • kafka

    About

    You say

    “Build a DeepStream pipeline that detects and tracks vehicles, then publishes to Kafka.”

    Card for the “Build a DeepStream video analytics pipeline” skill

    Skill published by nvidia under the CC-BY-4.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to build a DeepStream video analytics pipeline with TensorRT inference and messaging
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md4.7 KB
    • evals/evals.json12 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/best_practices.md34.3 KB
    • references/buffer_apis.md55.2 KB
    • references/docker_containers.md9.3 KB
    • references/gstreamer_plugins.md32.2 KB
    • references/kafka_messaging.md60.5 KB
    • references/media_extractor_advanced.md27.9 KB
    • references/metamux_config.md12.2 KB
    • references/nvds_msgapi_adapter.md28.4 KB
    • references/nvinfer_config.md22.9 KB
    • references/rest_api_dynamic.md11.8 KB
    • references/service_maker_api.md63.1 KB
    • references/streaming_sources.md16.5 KB
    • references/tracker_config.md50.7 KB
    • references/troubleshooting.md26.4 KB
    • references/use_cases_pipelines.md36.5 KB
    • references/utilities_config.md46.5 KB
    • skill-card.md5.1 KB
    • SKILL.md13.2 KB
    • skill.oms.sig8.3 KB

    Origin and licence

    Listed unmodified

    Author
    nvidia
    Source
    github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/deepstream-dev
    Licence
    CC-BY-4.0

    Notice

    « deepstream-dev » (nvidia, CC-BY-4.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.