OpenMontageInc/OpenMontage
Open-source agentic video production system that turns a plain-language brief into a finished video by having an AI agent handle research, scripting, asset generation, editing and composition.
Awesome AI Agents › Video Processing Agents
hypit-ai/hypit
Hypit gives AI agents such as Claude Code or Codex a way to work with video the same way they work with text: by giving them a language and toolset for describing and rebuilding a video's structure. A user drops in an existing video, and the agent analyzes it and reconstructs it as a complete, editable workflow covering footage selection, captions, B-roll insertion and effects, with every element anchored to words in the transcript rather than to raw timestamps. Because the representation is word-anchored, the agent can then generate variants of the cloned structure programmatically, which the project markets as going from one command to around a hundred output variants. The tagline pairs this with a claim of enabling reach in the hundreds of millions of views, reflecting its target audience of short-form content creators and growth teams who need many stylistic variations of a proven video format quickly. The project is written in TypeScript, requires a recent Node.js and pnpm toolchain, and ships documentation for a quickstart and for extending the system during development, alongside a separate Chinese-language README. It reached the top of GitHub's Trendshift rankings for TypeScript repositories shortly after release, indicating fast adoption among the agentic-video-editing audience. Rather than being a general-purpose video editor, Hypit is scoped specifically to the clone-and-remix workflow: taking an existing successful video as a template and letting an AI agent drive the mechanical work of reproducing its structure across many new outputs, leaving creative direction and asset sourcing to the human operator.
https://github.com/hypit-ai/hypit
Also in Video Processing Agents
HBAI-Ltd/Toonflow-app
Open-source AI short-drama production platform that carries a project from script and asset management through to finished video, organized as an end-to-end unmanned production pipeline.
GetStream/Vision-Agents
Open Vision Agents by Stream is a platform for building real-time, low-latency multi-modal AI agents that understand and interact with video content using advanced models and Stream's edge network.
RayVentura/ShortGPT
ShortGPT is an AI-powered framework that automates video content creation and editing for platforms like YouTube Shorts and TikTok, supporting multi-language voiceovers and automated footage sourcing.
dramaclaw/dramaclaw
Source-available AIGC video production pipeline that turns a manuscript into a finished short drama, handling character extraction, episode planning, scripts, storyboards, voice-over and final editing.
showlab/Awesome-Video-Diffusion
A curated list of recent diffusion models and resources for video generation, editing, restoration, and various AI-driven video applications.
nexu-io/html-video
Apache-2.0 toolkit that lets local coding agents turn HTML, CSS and data into real MP4 video through pluggable render engines, 21 animated templates and an optional AI soundtrack.
HKUDS/VideoAgent
Multi-agent framework for video understanding, editing and generation that parses user intent, builds a graph-based tool workflow and produces edited or newly created videos from natural language.