videoflow/videoflow

Python framework that facilitates the quick development of complex video analysis applications and other series-processing based applications in a multiprocessing environment.

What it solves

Videoflow is a framework for building distributed video and stream processing pipelines. It allows developers to define a processing graph (a directed acyclic graph) once and run it either locally for development or on Kubernetes for production scaling, without changing the code.

How it works

  • Graph-Based Architecture: Users describe a pipeline as a set of producers, processors, and consumers.
  • Distributed Execution: Each node in the graph runs as an independent worker (a subprocess locally or a pod on Kubernetes) that communicates via a NATS JetStream message broker.
  • Node Communication: Every node publishes its output to a specific broker subject and subscribes to the inputs of its parents, enabling complex topologies like fan-out and multi-parent joins.
  • Deployment: The framework handles the compilation of the graph into Kubernetes manifests, including GPU scheduling, health probes, and autoscaling.

Who it’s for

  • Developers building high-throughput video processing applications.
  • ML engineers needing to deploy computer vision models (object detection, tracking, pose estimation) in a distributed environment.
  • Teams requiring a seamless transition from local prototyping to Kubernetes-based production scaling.

Highlights

  • Hybrid Execution: Run the same pipeline locally or on Kubernetes with zero code changes.
  • Language Agnostic: Supports components written in any language as long as they are shipped as container images.
  • GPU Integration: Built-in support for GPU scheduling, including handling NVIDIA device plugins and time-slicing for shared GPU access.
  • Pre-built Components: Ships with off-the-shelf nodes for common vision tasks like segmentation and object detection.

Related

  • Project
    nndeploy/nndeploy

    A high-performance AI deployment framework that uses visual workflows to deploy AI models across desktop, mobile, and edge devices.

  • Project
    flyteorg/flyte

    Flyte 2 is an open‑source Python framework for defining, orchestrating and serving ML pipelines and AI agents. It lets you write ordinary Python functions as tasks, compose them into workflows, and run them locally or on a future Kubernetes‑native backend. The project includes a CLI, a developer‑focused TUI, and first‑class support for FastAPI model serving.

  • Project
    chatfire-AI/huobao-canvas

    Huobao Canvas is an open‑source, node‑based visual editor that lets you chain text, image, and video AI models from 11 providers on an infinite canvas. It offers a lightweight Node server for persistence and async run queues, Docker and Electron deployment options, and a single‑key setup via Huobao. Ideal for building multimodal creative pipelines without writing code.

  • Project
    Netflix/metaflow

    A human-centric framework for building and manage real-life AI and ML systems, streamlining the transition from prototyping to production deployment.

  • Project
    daydreamlive/scope

    A tool for running and customizing real-time, interactive generative AI video pipelines using autoregressive diffusion models and a composable architecture.