Who is OpenMontage for?

Suits creators and developers who already use an AI coding assistant and are comfortable installing Python, Node.js and FFmpeg; API keys for paid providers are optional but useful.

What can you build with OpenMontage?

Make a 60-second animated explainer about a technical topic from one prompt. Build a documentary-style montage from free stock footage with music and no narration. Recreate the pacing and structure of a Short or Reel you like, on a new topic. Produce a product film from approved still images using image-to-video models. Review a production's script, storyboard and costs on the Backlot board before final render.

How do I get started with OpenMontage?

Install Python 3.10+, FFmpeg and Node.js 18+, then clone the repo and run make setup. Open the folder in your AI coding assistant and describe the video you want. Commands from the README: git clone https://github.com/calesthio/OpenMontage.git; cd OpenMontage; make setup.

calesthio /

OpenMontage

Video production pipelines your AI coding assistant runs from a plain-language prompt

70.9k stars
8.7k stars since 3 Oct
Python
Updated 6 days ago
Some experience
Image, video & audio

Open on GitHub (opens in a new tab) Website (opens in a new tab)

Making a video usually means juggling many tools: research, script, voice, images, clips, music, captions and editing. OpenMontage puts that work behind your AI coding assistant. You describe the video in plain language, and the agent follows production pipelines and guide files stored in the repo.

It works with Claude Code, Cursor, Copilot, Windsurf and Codex. The agent calls tools for image and video generation, text-to-speech, music, FFmpeg and Remotion composition. The README says provider choices are scored and logged, and you approve the creative decisions along the way.

Unlike tools that only animate a few still images, it can also build a video from free stock footage and open archives. It can also start from a reference video (YouTube, Short, Reel, TikTok or a local clip) and propose similar concepts with cost estimates.

What it does

Prompt-to-video pipeline
The agent handles research, scripting, narration, music, word-level subtitles and final rendering. It runs self-review checks (ffprobe validation, frame sampling, audio levels, subtitle checks) before showing you the result.
Start from a reference video
Paste a video link or local clip and the agent analyzes transcript, pacing, scenes and style. You get 2-3 concepts, a tool path and a cost estimate before full production.
Real-footage mode
It can build a corpus from free stock footage and open archives, retrieve motion clips, and edit them into a timeline instead of animating stills.
Backlot live storyboard
A local board shows stages, the script, scene cards, provider decisions and spend as the pipeline runs. Asset generation pauses on a storyboard so you can approve visuals before rendering.
Cost and provider tracking
Each provider choice is scored across 7 dimensions with a decision log. The README's example videos list their costs, from about $1.33 to about $5.

What you could build

Make a 60-second animated explainer about a technical topic from one prompt.
Build a documentary-style montage from free stock footage with music and no narration.
Recreate the pacing and structure of a Short or Reel you like, on a new topic.
Produce a product film from approved still images using image-to-video models.
Review a production's script, storyboard and costs on the Backlot board before final render.

Get started

Install Python 3.10+, FFmpeg and Node.js 18+, then clone the repo and run make setup. Open the folder in your AI coding assistant and describe the video you want.

git clone https://github.com/calesthio/OpenMontage.git

cd OpenMontage

make setup

Commands are copied from the project's README. Read it on GitHub for the full setup.