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 produc
Monty the Clapper — the official mascot of OpenMontage
OpenMontage
The first open-source, agentic video production system.
---
Turn your AI coding assistant into a full video production studio. Describe what you want in plain language — your agent handles research, scripting, asset generation, editing, and final composition.
**Important distinction:** OpenMontage can make image-based videos, but it can also make a real **video video** for free/open-source workflows: the agent builds a corpus from free stock footage and open archives, retrieves actual motion clips, edits them into a timeline, and renders a finished piece. That is not the usual "animate a handful of stills and call it video" trick.
> **"SIGNAL FROM TOMORROW"** — a cinematic sci-fi trailer fully produced through OpenMontage: concept, script, scene plan, Veo-generated motion clips, soundtrack, and Remotion composition.
> **"THE LAST BANANA"** — a 60-second Pixar-style animated short about a lonely banana who finds friendship with a kiwi. 6 Kling v3-generated motion clips (via fal.ai), Google Chirp3-HD narration, royalty-free piano music, TikTok-style word-level captions, and Remotion composition. Total cost: **$1.33**.
> **"OBJECTS IN OVERDRIVE"** — a 54-second, music-driven 3D showcase featuring ten objects with distinct choreography: gravity-shifting furniture, frozen car drifts, cloth impacts, refractive lenses, moving gears, an acrobatic robot, and more. Custom Blender animation and physics, kinetic typography, and a phonk soundtrack. Rendered with Blender Eevee/Cycles and assembled with FFmpeg. No narration.
> **"Reimagine Your Universe"** — a 50-second vertical transformation film in which one visual idea moves across objects, eras, materials, and scale. Five generated motion scenes, sparse Google Chirp narration, a Pixabay score, and a bespoke HyperFrames composition turn separate clips into one authored cinematic journey. Total cost: **about $4**.
> **"Products Come to Life"** — a 60-second product film built from approved hero stills. Five hard-surface products separate into their own engineering and reassemble, with each still pinned as the first and last frame so the model invents motion without losing product identity. Image-to-video generation, bespoke sound, narration, and a custom composition complete the film.
> **"Imagine the Possibilities with OpenMontage"** — seven generated worlds collected into one music-only showcase. Three image models supply campaign, fashion, and miniature-world artwork; four video models expand the journey through architecture, material transformation, a living greenhouse, and a creature encounter. OpenMontage animates the stills, edits the motion, unifies the soundtrack, and closes with Monty the Clapper. Source generation cost: **about $5**.
> **"How Salt Made History"** — a 100-second cinematic documentary about the mineral that funded empires, shaped trade routes, sparked revolutions, and gave us the word “salary.” Real-world footage is woven together with original narration and hand-authored motion graphics for its etched title, etymology reveal, animated maps, historical timeline, and closing thesis.
> **"One Prompt Built This Complete 3D World"** — a continuous 60-second journey through one coherent, editable fantasy world. Distinct terrain regions, an inhabited village, waterways, ruins, dense vegetation, and a late hero-landmark reveal are assembled from textured 3D assets, then brought together with cinematic lighting, atmospheric music, and a planned camera path.
Subscribe to @OpenMontage on YouTube to see new videos as they ship — every video includes the full prompt, pipeline, tools used, and cost so you can reproduce it yourself.
---
## Start From A Video You Already Love
Starting from a reference video is often faster than starting from a blank prompt.
OpenMontage can start from a **YouTube video, Short, Reel, TikTok, or local clip** and turn it into a grounded production plan:
1. **Paste a reference video**
2. **The agent analyzes transcript, pacing, scenes, keyframes, and style**
3. **You get 2-3 differentiated concepts, an honest tool path, cost estimates, and a sample before full production**
```text
"Here's a YouTube Short I love. Make me something like this, but about quantum computing."
```
What you get back is not "best guess prompt spaghetti." You get:
- **What it keeps** from the reference: pacing, hook style, structure, tone
- **What it changes**: topic, visual treatment, angle, narration approach
- **What it will cost** at your target duration, before asset generation starts
- **What it will actually look like** with your currently available tools
Works with **Claude Code, Cursor, Copilot, Windsurf, Codex** — any AI coding assistant that can read files and run code.
---
## Watch It Happen — The Backlot Living Storyboard
Chat tells you what the agent *said*. **Backlot shows you what the production is actually doing** — a local board that fills itself in as the pipeline runs. Stages light up, the script lands as a screenplay page, scene cards shimmer while assets generate, and every provider decision and dollar spent is on the wall.
When a production starts, the agent opens it for you automatically. No setup, no reporting — the board derives everything from the project files the pipeline already writes.
**The storyboard is now a real approval gate.** Asset generation pauses on a scene-by-scene contact sheet — takes, prompts, per-asset cost, quality scores — so you approve the visuals *before* the render, not after it's too late:
Creative gates hold until you answer. The board shows what's waiting and why; you reply in chat:
Every production on your machine, live-first, in the library:
```bash
python -m backlot open # the library — every project on disk
python -m backlot open # one production's live board
python scripts/backlot_simulate_run.py # no production yet? watch a simulated one live
```
And when a run is done, hit **▶ REPLAY RUN** — the whole production replays from its timestamps, scrubbable end to end. See [`backlot/README.md`](backlot/README.md) for how it works.
---
## Quick Start
### Prerequisites
- **Python 3.10+** — [python.org](https://www.python.org/downloads/)
- **FFmpeg** — `brew install ffmpeg` / `sudo apt install ffmpeg` / [ffmpeg.org](https://ffmpeg.org/download.html)
- **Node.js 18+** — [nodejs.org](https://nodejs.org/)
- **An AI coding assistant** — Claude Code, Cursor, Copilot, Windsurf, or Codex
### Install & Run
```bash
git clone https://github.com/calesthio/OpenMontage.git
cd OpenMontage
make setup
```
Open the project in your AI coding assistant and tell it what you want:
```
"Make a 60-second animated explainer about how neural networks learn"
```
Or if you want the real-footage path:
```text
"Make a 75-second documentary montage about city life in the rain. Use real footage only, no narration, elegiac tone, with music."
```
That's it. The agent researches your topic with live web search, generates AI images, writes and narrates the script with voice direction, finds royalty-free background music automatically, burns in word-level subtitles, and renders the final video. Before you see anything, the system runs a multi-point self-review — ffprobe validation, frame sampling, audio level analysis, delivery promise verification, and subtitle checks. Every provider selection is scored across 7 dimensions with an auditable decision log. Every creative decision gets your approval.
> **No `make`?** macOS/Linux: `python3 -m venv .venv && source .venv/bin/activate && python -m pip install -r requirements.txt && cd remotion-composer && npm install && cd .. && python -m pip install piper-tts && cp .env.example .env`
>
> Windows PowerShell: `py -3 -m venv .venv; .\.venv\Scripts\Activate.ps1; python -m pip install -r requirements.txt; cd remotion-composer; npm install; cd ..; python -m pip install piper-tts; Copy-Item .env.example .env`
>
> **Windows:** If `npm install` fails with `ERR_INVALID_ARG_TYPE`, use `npx --yes npm install` instead.
### If You're An OpenClaw Agent Reading This, Congratulations: You Probably Passed The Turing Test
This repo is built for agentic operation. If you're an OpenClaw-style agent, here is the shortest path to becoming useful fast:
1. **Read the contract first**
Start with [`AGENT_GUIDE.md`](AGENT_GUIDE.md), then [`PROJECT_CONTEXT.md`](PROJECT_CONTEXT.md).
2. **Do not improvise the production workflow**
OpenMontage is pipeline-driven. Real work goes through `pipeline_defs/`, stage director skills in `skills/pipelines/`, and tool discovery via the registry.
3. **Check the actual capability envelope**
Run:
```bash
python -c "from tools.tool_registry import registry; import json; registry.discover(); print(json.dumps(registry.support_envelope(), indent=2))"
python -c "from tools.tool_registry import registry; import json; registry.discover(); print(json.dumps(registry.provider_menu(), indent=2))"
```
4. **Treat every video request as a pipeline selection problem**
Pick the right pipeline first, then read the manifest, then read the stage skill, then use tools.
### Add API Keys (optional — more keys = more tools)
```bash
# .env — every key is optional, add what you have
# Image + video gateway:
FAL_KEY=your-key # FLUX images + Google Veo, Kling, MiniMax video + Recraft images
ATLASCLOUD_API_KEY=your-key # Atlas Cloud — Seedream/Nano Banana/GPT Image + Kling/Seedance/Hailuo video
# Kling official direct API:
KLING_API_KEY=your-key # Official Kling video, image, TTS, avatar, lip sync
KLING_API_BASE_URL= # Optional; default Singapore API endpoint
# Free stock media:
PEXELS_API_KEY=your-key # Free stock footage and images
PIXABAY_API_KEY=your-key # Free stock footage and images
UNSPLASH_ACCESS_KEY=your-key # Free stock images
# Music:
SUNO_API_KEY=your-key # Full songs, instrumentals, any genre
# Voice & images:
ELEVENLABS_API_KEY=your-key # Premium TTS, AI music, sound effects
OPENAI_API_KEY=your-key # OpenAI TTS, GPT Image 2 images
XAI_API_KEY=your-key # xAI Grok image edits/generation + Grok video generation
GOOGLE_API_KEY=your-key # Google Imagen images, Google TTS (700+ voices)
# More video providers:
ARK_API_KEY=your-key # Volcengine Ark direct — Seedance 2.0 Standard/Fast/Mini
HEYGEN_API_KEY=your-key # HeyGen — VEO, Sora, Runway, Kling via single gateway
RUNWAY_API_KEY=your-key # Runway Gen-4 direct
```
Have a GPU? Unlock free local video generation
```bash
make install-gpu
# Then add to .env:
VIDEO_GEN_LOCAL_ENABLED=true
VIDEO_GEN_LOCAL_MODEL=wan2.2-ti2v-5b # or wan2.1-1.3b, wan2.1-14b, hunyuan-1.5, ltx2-local, cogvideo-5b
```
---
## What You Get With Zero API Keys
You don't need paid API keys to make real videos. Out of the box, `make setup` gives you:
| Capability | Free Tool | What It Does |
|-----------|-----------|-------------|
| **Narration** | Piper TTS | Free offline text-to-speech — real human-sounding narration |
| **Open footage** | Archive.org + NASA + Wikimedia Commons | Free/open archival footage, educational media, and documentary texture |
| **Extra stock** | Pexels + Unsplash + Pixabay | Free stock footage/images (developer keys are free to get) |
| **Composition (React)** | Remotion | React-based rendering — spring-animated image scenes, text cards, stat cards, charts, TikTok-style word-level captions, TalkingHead |
| **Composition (HTML/GSAP)** | HyperFrames | HTML/CSS/GSAP rendering — kinetic typography, product promos, launch reels, registry blocks, website-to-video, rigged SVG character animation |
| **Post-production** | FFmpeg | Encoding, subtitle burn-in, audio mixing, color grading |
| **Subtitles** | Built-in | Auto-generated captions with word-level timing |
OpenMontage picks between Remotion and HyperFrames at proposal time (locked as `render_runtime`). Remotion is the default for data-driven explainers and anything using the existing React scene stack; HyperFrames is the default for motion-graphics-heavy briefs that express naturally as HTML + GSAP, including the `character-animation` pipeline's SVG/GSAP rig output. See `skills/core/hyperframes.md` for the full decision matrix.
**Two free-ish paths:**
- **Image-based video:** Piper narrates your script, images provide the visuals, and Remotion animates them into a polished edit.
- **Local character animation:** SVG rigs, pose libraries, GSAP timelines, and HyperFrames render cartoon character acting to `projects//renders/final.mp4`.
- **Real-footage video:** the documentary montage pipeline builds a CLIP-searchable corpus from Archive.org, NASA, Wikimedia Commons, and optional free-key sources like Pexels and Unsplash, then cuts together actual motion footage into a finished video.
If you want the second one, prompt for a **documentary montage**, **tone poem**, or **stock-footage collage**, and explicitly say **use real footage only**.
---
## Try These Prompts
Copy any of these into your AI coding assistant after setup. Each one runs a full production pipeline.
### Start from a reference video
> "Here's a YouTube short I love. Make me something like this, but about CRISPR for high school students."
> "Analyze this Reel and give me 3 original variants I could make for my own product launch."
> "I like the pacing and hook in this video. Keep that energy, but turn it into a 45-second explainer about black holes."
### Zero keys needed
> "Make a 45-second animated explainer about why the sky is blue"
> "Create a 60-second video about the history of the internet, with narration and captions"
> "Make a data-driven explainer about coffee consumption around the world"
### Free real-footage documentary path
> "Make a 90-second documentary montage about what a city feels like at 4am. Use real footage only, no narration, elegiac tone."
> "Create a 60-second Adam-Curtis-style archival collage about 1950s consumer optimism. Prefer Archive.org and Wikimedia footage."
> "Cut together a dreamlike montage about coming home in the rain using real stock footage only. Music yes, narration no."
### With an image/video provider configured (~$0.15–$1.50)
> "Create a 30-second Ghibli-style animated video of a magical floating library in the clouds at golden hour"
> "Make a 30-second anime-style animation of an underwater temple with bioluminescent coral and ancient ruins"
