{"data":{"slug":"prominenceai-deepstream-services-library","name":"deepstream-services-library","tagline":"Library of on-demand DeepStream Pipeline Services for AI-based video analytics","github_url":"https://github.com/prominenceai/deepstream-services-library","owner":"prominenceai","repo":"deepstream-services-library","owner_avatar_url":"https://avatars.githubusercontent.com/u/72884507?v=4","primary_language":"C++","stars":346,"forks":70,"topics":["ai","computer-vision","deep-learning","deepstream","edge-computing","gstreamer","inference","jetson","multiobject-tracking","nvidia","nvidia-deepstream-sdk","nvidia-gpu","object-detection","python","video-analytics","xavier","yolo8","yolov4","yolov5"],"archived":false,"github_pushed_at":"2025-03-17T03:53:48+00:00","maintenance_label":"Dormant","stars_delta_30d":-1,"url":"https://www.graphcanon.com/tools/prominenceai-deepstream-services-library","markdown_url":"https://www.graphcanon.com/tools/prominenceai-deepstream-services-library.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/prominenceai-deepstream-services-library","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=prominenceai-deepstream-services-library","description":"A shared library of on-demand DeepStream Pipeline Services for Python and C/C++","homepage_url":null,"license":"MIT","open_issues":65,"watchers":15,"ai_summary":"prominenceai/deepstream-services-library provides on-demand service libraries for Python and C/C++, supporting computer vision tasks such as object detection through integration with the NVIDIA DeepStream SDK","readme_excerpt":"# Intelligent Audio and Video Analytics (IAVA)\nA library of on-demand DeepStream Pipeline services. Written in C++ 17 with an `extern \"C\"` API, The DeepStream Services Library (DSL) can be called from both C/C++ and Python applications.\n\n## Examples\n\n### C++\n\n```C++\n#include <DslApi.h>\n\n// New V4L2 Source\nuint retval = dsl_source_v4l2_new(L\"my-web-cam-1\", L\"/dev/video0\");\n```\n\n### Python3\n\n```Python\nfrom dsl import *\n\n# New V4L2 Source\nretval = dsl_source_v4l2_new('my-web-cam-1', '/dev/video0')\n```\n\nDSL is built on the NVIDIA® [DeepStream SDK](https://developer.nvidia.com/deepstream-sdk), _\"A complete streaming analytics toolkit for AI-based video and image understanding, as well as multi-sensor processing.\"_,\n\nThe DeepStream SDK and DSL use the open source [GStreamer](https://gstreamer.freedesktop.org/),  _\"An extremely powerful and versatile framework for creating streaming media applications\"_.\n\n---\n\n## Contributing\n\nDSL is released under the [MIT License](LICENSE). Contributions are welcome and greatly appreciated. Please review our [code of conduct](/CODE_OF_CONDUCT.md).\n\n***Please report issues!***\n\n## DSL Branching Workflow\n\n\n\n1. `Master` is always the latest release and is only updated once per release.\n2. `Develop` is the next release currently in development. The branch will be named with the next release label.\n3. `Feature` all work is done on feature branches, named for the feature under development. \n\nAll pull requests should be made against the current `Develop` branch.\n\n## Discord\nCome join us on [Discord](https://discord.gg/MJvY9jjpAK), an informal place to chat, ask questions, discuss ideas, etc.\n\n## DSL Users Guide\n\n* [Release Notes](/Release%20Notes/dsl-releases.md)\n* [Overview](/docs/overview.md)\n* [Installing Dependencies](/docs/installing-dependencies.md)\n* [Building and Importing DSL](/docs/building-dsl.md)\n* [API Reference](/docs/api-reference-list.md)\n  * [Pipeline](/docs/api-pipeline.md)\n  * [Player](/docs/api-player.md)\n  * [Source](/docs/api-source.md)\n  * [Tap](/docs/api-tap.md)\n  * [Video Dewarper](/docs/api-dewarper.md)\n  * [Preprocessor](/docs/api-preproc.md)\n  * [Inference Engines and Servers](/docs/api-infer.md)\n  * [Multi-Object Tracker](/docs/api-tracker.md)\n  * [Segmentation Visualizer](/docs/api-segvisual.md)\n  * [Tiler](/docs/api-tiler.md)\n  * [Demuxer and Splitter](/docs/api-tee.md)\n  * [Remuxer](/docs/api-remuxer.md)\n  * [On-Screen Display](/docs/api-osd.md)\n  * [Sink](/docs/api-sink.md)\n  * [Branch](/docs/api-branch.md)\n  * [Component](/docs/api-component.md)\n  * [Custom Component](/docs/api-gst.md)\n  * [Pad Probe Handler](/docs/api-pph.md)\n  * [ODE Trigger](/docs/api-ode-trigger.md)\n  * [ODE Accumulator](/docs/api-ode-accumulator.md)\n  * [ODE Acton](/docs/api-ode-action.md)\n  * [ODE Area](/docs/api-ode-area.md)\n  * [ODE Heat-Mapper](/docs/api-ode-heat-mapper.md)\n  * [Display Type](/docs/api-display-type.md)\n  * [Mailer](/docs/api-mailer.md)\n  * [WebSocket Server](/docs/api-ws-server.md)\n  * [Message Broker](/docs/api-msg-broker.md)\n  * [Info API](/docs/api-info.md)\n* [Examples](/docs/examples.md)\n  * [Basic Inference Pipelies](/docs/examples-basic-pipelines.md)\n  * [Multiple Sources, Tilers, and Demuxers](/docs/examples-sources-tiler-demuxer.md)\n  * [Advanced Inference Pipelies](/docs/examples-advanced-pipelines.md)\n  * [Smart Recording](/docs/examples-smart-recording.md)\n  * [Object Detection Event (ODE) Services](/docs/examples-ode-services.md)\n  * [Encoding Frames to JPEG](/docs/examples-encode-and-save-frame.md)\n  * [Dewarping and Segmentation](/docs/examples-dewarping-and-segmentation.md)\n  * [Dynamic Pipelines](/docs/examples-dynamic-pipelines.md)\n  * [Custom Components](/docs/examples-custom-components.md)\n  * [Working with OpenCV](/docs/examples-opencv.md)\n  * [Diagnostics and Utilites](/docs/examples-diagnaostics-and-utilities.md)\n  * [Tkinter Reference App](/docs/examples-tkinter.md)\n  * [HTML WebRTC Client](/docs/examples-webrtc-html.md)\n* [Using VS Code](/docs/vscode.md)\n*","github_created_at":"2019-08-23T19:13:42+00:00","created_at":"2026-07-11T12:30:26.248272+00:00","updated_at":"2026-09-24T06:00:54.266216+00:00","categories":[{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"c","name":"c++"},{"slug":"gstreamer","name":"gstreamer"},{"slug":"nvidia-deepstream-sdk","name":"nvidia deepstream sdk"},{"slug":"object-detection","name":"object-detection"},{"slug":"python","name":"python"},{"slug":"video-analytics","name":"video analytics"}],"trust":{"provenance":{"is_fork":false,"github_id":204056467,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-24T06:00:53.362Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":556,"last_release_at":"2025-03-17T03:53:48Z","stars_delta_30d":-1,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:30:27.855Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-24T06:00:53.804Z"},"languages":{"value":["c++"],"source":"github.language","observed_at":"2026-09-24T06:00:53.804Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-24T06:00:53.804Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When developing AI-based video analytics applications that require integration with NVIDIA's GPU-accelerated tools.","For projects demanding high-performance inference and real-time video processing, leveraging both Python and C++ interfaces.","If you need to implement comprehensive multi-object tracking or segmentation visualizer using edge computing capabilities."],"when_not_to_use":["When the primary development environment is not Linux-based, as DeepStream Services Library has NVIDIA-specific dependencies.","For applications needing real-time analytics on platforms that do not support NVIDIA GPUs.","If the project does not require object detection or segmentation visualization features for video streams and focuses more on other aspects of computer vision."],"source":"enrich:decision_facts","observed_at":"2026-07-17T01:06:30.795Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"A library of on-demand DeepStream Pipeline services for Python and C++, supporting computer vision tasks such as object detection through integration with the NVIDIA DeepStream SDK."}]}}