Open-source agentic video production system that turns an AI coding assistant into a video studio.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
OpenMontage is an open-source, agent-driven video production system. It is a repository of pipelines, tools and agent skill files that an AI coding assistant (Claude Code, Cursor, Copilot, Windsurf, Codex) reads and executes. The user describes a video in plain language, and the agent handles research, scripting, asset generation, editing and final composition.
The GitHub repo lists 12 production pipelines, 100+ tools and 700+ agent skill and production-knowledge files. Compositions are rendered with Remotion, HyperFrames, Blender or FFmpeg. Generation can use external providers such as Veo, Kling (via fal.ai) and Google Chirp TTS. A free workflow instead builds a corpus from stock footage and open archives and edits real motion clips. It can also start from a reference video (YouTube, Short, Reel, TikTok or local clip), analyse its pacing and style, and propose concepts with cost estimates before production.
It runs locally under the user's own coding assistant, so output quality and cost depend on the assistant and on whichever third-party generation APIs are configured. The README's example videos report costs of roughly $1.33 to $5 in generation fees. The code is licensed AGPL-3.0.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Open-source project that turns an AI coding assistant into a video production studio handling research, scripting, asset generation, editing and composition. Features 12 production pipelines and 400 agent skills; shown with a sci-fi trailer example.
Closest neighbours by meaning, not just by category.
Model · Lightricks
Open-weights Lightricks video model with native audio, multi-shot generation, auto duration and up to 4K output.
Model · Google
Faster Gemini Omni variant from Google for generating and editing video from references and text prompts.
Model · JD
Open-weights 16B autoregressive diffusion model from JD for real-time, instruction-guided editing of streaming video.
Model · OpenAI
OpenAI's image generation and editing model family, accessed via the API and ChatGPT.
Model · SenseTime
Open-weights 27B model from SenseTime that creates short videos by generating and rendering executable code.
App · OpenAI
OpenAI's open-source coding agent that runs in the terminal, with voice control and a new code review experience.
