OpenMontage
OpenMontageInc/OpenMontageReviewed by AI
Checked by RepoPicks Radar on
What is OpenMontage?
A set of Python tools, YAML pipelines and Markdown skill files that your AI coding assistant (Claude Code, Cursor, Copilot, Windsurf, Codex) reads to build a video end to end: research, script, narration, generated images or stock footage, subtitles and the final render. For video creators who already work inside one of those assistants. You clone the repo and run `make setup`, with Python 3.10+, FFmpeg and Node.js on a patched 22.x (22.23.4+), 24.x (24.22.1+) or 26.x (26.12.1+) release. Provider keys are optional.
OpenMontage is free and open source (AGPL-3.0) and can replace InVideo AI, Pictory, and Synthesia.
How easy is it to install OpenMontage?
D · terminal, several tools or a specific graphics card · Windows
- Windows D
- macOS D
- Linux D
Grade D on Windows, macOS and Linux alike: there is nothing to download (0 GitHub releases), so you clone the repository and run `make setup` in a terminal, and you need Python 3.10+, FFmpeg and a patched Node.js release on the 22.x (22.23.4+), 24.x (24.22.1+) or 26.x (26.12.1+) line (`.node-version` selects 22.23.4), plus one of the supported AI coding assistants to drive it. The free local video generation path also asks for a graphics card.
Coming soon: install in 1 click with the RepoPicks app.
OpenMontage on GitHub
- Stars
- 79,396on Nov 10, 2026
- Downloads
- —all releases
- Growth
- +3,423stars in 7 days
Stars over time
Facts
- Runs on
- Windows, macOS, Linux
- You need to install
- Python, Node.js, FFmpeg, Other tools
- To build from source
- Python, Graphics card, FFmpeg
- Disk space
- 900 MB–4.2 GB · estimate
- Accounts or keys
- fal.ai (FAL_KEY / FAL_AI_API_KEY), OpenAI, Google (Gemini, Imagen, Cloud TTS), ElevenLabs, Replicate, Kling, Runway, HeyGen, Suno, Hugging Face, Pexels, Pixabay
- Cost
- Free · AGPL-3.0 code, no purchase. The README describes a path with no paid keys (Piper voices, open archives, Remotion, FFmpeg) and its own examples quote "Total cost: $1.33" for one 60-second video and "~$1–$3" for a full setup when paid providers are used.
- License
- AGPL-3.0 (Copyleft)
- Last change on GitHub
- Nov 9, 2026
OpenMontage risk signals (6)
- AttentionOwner account created recently
Owner account created 47 days ago
automatic check
- Attentionpaid provider spend on your accounts
.env.example lists keys for 29 provider accounts and the work runs on your own accounts; the README's examples quote "Total cost: $1.33" for one 60-second video and "~$1–$3" for a full setup, with a described default total budget cap of $10.
AI review
- Infono releases and early version number
Project facts: 0 GitHub releases and 323 open issues; setup.py declares version="0.1.0". You install whatever is on the main branch that day.
AI review
- Infoagpl network copyleft
LICENSE is the GNU Affero General Public License v3: if you offer a modified version to other people over a network, you must give them the source code of that version.
AI review
- Infocode fetched from npm at run time
README on the HyperFrames renderer: "Consumed via `npx hyperframes`; no monorepo checkout needed" — that package is pulled from npm when a production runs.
AI review
- Inforepository owner mismatch
Project facts give the repository as OpenMontageInc/OpenMontage, while the README's clone command and badges still point to github.com/calesthio/OpenMontage.
AI review
Evidence is shown in its original language.
What Radar could not check about OpenMontage
- Whether `make setup` finishes on each system; the README itself notes that on Windows `npm install` may fail with ERR_INVALID_ARG_TYPE and suggests `npx --yes npm install`.
- What one video really costs on your provider accounts, and whether the budget cap and approval thresholds hold in practice.
- What the AI coding assistant itself costs in tokens for a full production, which is on top of the provider keys.
- Real disk use after the Python packages, the Node modules and any local video models are downloaded.
- What the `npx hyperframes` package downloads and runs at production time.
- Whether the no-paid-key path (Piper voices, open archives, Remotion) produces videos you would publish.
- Whether the quality gates, self-review and decision log behave as the README describes.