reactor-sdk

Build real-time video AI apps using Reactor SDKs over WebRTC.

4|2|Updated Apr 14, 2026
One-click install
npx skills add https://github.com/reactor-team/reactor-skills --skill reactor-sdk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: reactor-sdk
Source: https://github.com/reactor-team/reactor-skills/tree/main/skills/reactor-sdk
Command: npx skills add https://github.com/reactor-team/reactor-skills --skill reactor-sdk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @reactor-team/js-sdk, reactor-sdk, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill facilitates building real-time video AI applications by providing SDKs to connect to GPU-powered Reactor models over WebRTC.

Core Features & Use Cases

  • SDK Integration: Offers JavaScript and Python SDKs to build web and mobile AI applications.
  • WebRTC Streaming: Streams video to frontends over WebRTC with command-based control.
  • Auth and Control: Handles JWT authentication for Reactor models and manages connection lifecycles.
  • Use Case: A web app uses this Skill to stream real-time video processing to a frontend, where it generates and displays live video transformations based on user commands.

Quick Start

Instantiate the Reactor SDK, create a JWT token, connect to the Reactor model, and publish the video input.

Frequently Asked Questions about reactor-sdk

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build real-time video AI applications using WebRTC?

To build real-time video AI applications with WebRTC, use Reactor SDKs to stream video to frontends, manage JWT authentication, and execute video-to-video transformations using GPU-powered models.

What is the best way to stream GPU-powered video models to a web frontend?

Streaming GPU-powered video models to a web frontend is best achieved using SDKs that connect over WebRTC with command-based control, allowing live video transformations based on user inputs.

Do I need JWT authentication to connect to Reactor models over WebRTC?

JWT authentication is required to securely connect to Reactor models over WebRTC. The SDK manages the connection lifecycle by handling JWT token creation and authentication.

Can I use JavaScript and Python SDKs for real-time video transformations on mobile?

JavaScript and Python SDKs support real-time video transformations on mobile and web frontends by connecting to GPU-powered Reactor models like Helios and SANA-Streaming.

How to set up video-to-video transformations for live streaming applications?

Setting up video-to-video transformations for live streaming requires installing the @reactor-team/js-sdk or reactor-sdk, instantiating the SDK, creating a JWT token, connecting to a Reactor model, and publishing the video input.