calesthio/OpenMontage
OpenMontage
World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.
GitHub metrics
- Stars
- 68K
- +5K this week
- Forks
- 8.6K
- 30-day growth
- —
- Open issues
- 111
| Day | GitHub stars |
|---|---|
| 2026-10-04 | 62700 |
| 2026-10-10 | 65973 |
| 2026-10-13 | 67714 |
What it does
OpenMontage is a Python toolkit that turns an AI coding assistant such as Claude Code, Cursor, Copilot, Windsurf or Codex into a video production setup. You describe the video, and the assistant moves through fixed stages: research, proposal, script, scene plan, assets, edit and compose. No separate orchestrator program runs the show. The assistant reads YAML pipeline manifests and a Markdown director skill for each stage, then calls the Python tools itself.
The repository has pipelines for animated explainers, cinematic trailers, documentary montages, talking-head edits, screen demos, podcast clips, and localization with dubbing, among others. It connects to many providers, including Kling, Veo, Runway, FLUX, ElevenLabs and Suno, and to local options: Piper for speech, WAN or Hunyuan video models on a GPU, and Remotion, HyperFrames and FFmpeg for rendering. With no API keys at all it can still narrate with Piper, pull footage from Archive.org, NASA and Wikimedia Commons, and render with Remotion.
Creative stages wait for your approval, and a local board called Backlot shows each stage, the generated assets and the money spent. Budget controls estimate costs before generation, with a default total cap of $10 and a confirmation step for any single action above $0.50.
Why it matters
The README sets OpenMontage against tools that return one clip per prompt: it runs a whole production from research to a rendered file and logs which provider it chose for each step and why. Its documentary pipeline cuts videos from real archival and stock footage, so a finished result does not depend on paid video generation. The orchestration rules are plain YAML and Markdown files that you can read and change.
Main features
- Pipelines ranging from animated explainers to documentary montages and dubbing
- Seven stages: research, proposal, script, scene plan, assets, edit, compose
- Zero-key path with Piper narration, open archives and Remotion rendering
- Optional local GPU video generation with WAN, Hunyuan, LTX-Video or CogVideo
- Approval gates and the Backlot board for checking scenes before the render
- Cost estimates, spend caps and per-action approval thresholds
- Post-render checks with ffprobe, frame sampling and audio level analysis
- Output profiles for YouTube, Shorts, Reels, TikTok, LinkedIn and 21:9 cinematic
Who it's for
- Claude Code, Cursor, Copilot, Windsurf or Codex users who want explainers, trailers or social clips from a written brief
- Creators who want to start from a reference video and see concepts and cost estimates before anything is generated
- Developers who want to add their own tools or pipelines to an open video stack
- People on no budget who can work with stock footage, open archives and offline narration
Strengths
- Produces image-based and real-footage videos without paid API keys
- Scores each provider choice and logs it with the alternatives in a decision trail
- Keeps orchestration in readable YAML and Markdown files you can edit
- Builds budget limits and human approval gates into every pipeline
Limitations
- AGPL-3.0 licence, which brings source-sharing duties for modified versions offered as a network service
- No tagged GitHub releases; setup is from a clone of the repository
- Local LLM support through Ollama and LM Studio is listed as coming soon
- Generated-video runs cost money: the README estimates about $0.15 to $3 per prompt with paid providers
Getting started
Requirements: Python 3.10+, FFmpeg, Node.js 18+ (HyperFrames needs Node.js 22+) and an AI coding assistant; API keys and a GPU are optional.
Always follow the official instructions in the README on GitHub. This overview is our summary, not a copy.
Sources
- calesthio/OpenMontageRepositoryPrimarygithub.com
- OpenMontage Studio — your creative workspace, powered by AI agentsOfficial sitePrimaryopenmontage.video
- raw.githubusercontent.com/calesthio/OpenMontage/main/README.mdWeb
- github.com/calesthio/OpenMontage/releasesRepositoryPrimary