actionow-ai/vvv

★ 439⑂ 124

Build a video template once, reuse it across coding agents. Editable Remotion templates and an Agent Skill for Claude Code, Codex and 25+ agents.

About actionow-ai/vvv

actionow-ai/vvv is an open-source project on GitHub, mainly written in Python. Build a video template once, reuse it across coding agents. Editable Remotion templates and an Agent Skill for Claude Code, Codex and 25+ agents. It currently holds 439 stars and 124 forks with 0 open issues, and was last pushed on an unknown date (repository created unknown).

Project Overview

Git Homed tracks it on the Today's Trending board.

GitHub Repository Details

Repository actionow-ai/vvv · default branch - · size 0 KB · watchers 0 · source: GitHub REST API and repository README

README

https://github.com/actionow-ai/vvv/blob/HEAD/Vibe Vision Video: build a template once, reuse it across agents. Open-source video templates for coding agents.

Swap in your photos and words for a new film.
Or bring a film you love and get your own version.

License Website Linux.do Claude Code Agent Skills MCP

Website · 简体中文 · Get started · Templates · Community · Docs

Made with the templates

https://github.com/actionow-ai/vvv/blob/HEAD/Doodle: a watercolor heart blooms behind We're married!
Doodle · hand-drawn
https://github.com/actionow-ai/vvv/blob/HEAD/Album: rounded-card story spreads
Album · clean album
https://github.com/actionow-ai/vvv/blob/HEAD/DV Story: photo pages on the PLAY screen with typed captions
DV Story · camcorder
https://github.com/actionow-ai/vvv/blob/HEAD/Comedy: the wrong-childhood-photo gag
Comedy · comic opener
https://github.com/actionow-ai/vvv/blob/HEAD/Starter: names typed in over a beat-cut photo reel
Starter · beat-cut reel
https://github.com/actionow-ai/vvv/blob/HEAD/Album 9:16: street spreads in the vertical short
Album 9:16 · vertical short

Click a loop for the full preview with sound. All rendered straight from the templates and passing vvv check; the couples and photos are fictional. All templates, formats and styles

Say one sentence. Your agent does the rest.

Picking the template, placing photos, writing copy, rendering, checking and delivering all happen in the conversation. You watch the sample and say what to change.

Use the vvv skill to make a 9:16 wedding short from the photos in ./photos. We are Lin Yizhou and Xu Zhixia, married on October 18. Show me a checked sample first.

Add it to your agent, any one of:

| Agent | Install | |---|---| | Claude Code | /plugin install vvv --marketplace actionow-ai/vvv (the plugin includes the templates) | | Codex, Cursor, Gemini CLI, Copilot and 20+ more | npx skills add actionow-ai/vvv, then clone this repository and set VVV_KIT (details) | | WorkBuddy | Upload the skill ZIP from Releases under 技能 → 添加技能 (details) | | Any MCP client | claude mcp add --transport http vvv https://mcp.vibevision.video/mcp to browse templates and guides with no install |

Rendering runs on your machine, which needs Python 3.9+, Node.js 26 and npm; the agent installs everything else.

One template, every new film

The scenes, layouts, timing and checks are built once. A new film changes only what belongs to it.

Built onceScene structure and camera moves · layouts for 16:9 and 9:16 · beat-planned timing · render checks
Changed per filmPhotos · names and dates · every line of copy · music and format

vvv.py describe tells the agent each template's photo slots, copy fields and settings, and validate catches bad inputs before a render. The agent changes the template's inputs first and its React/TypeScript source only where the brief needs it. Reuse is meant to save the tokens otherwise spent redesigning, regenerating and debugging the same video code; no comparative benchmark is published yet (see the roadmap).

Show it a film you love. Get your own.

https://github.com/actionow-ai/vvv/blob/HEAD/A filmstrip passing through a beat grid and becoming a V: a reference measured and rebuilt

Give your agent a reference video and the attachments that make it yours: photos, a logo, copy, music. It studies how the reference works and rebuilds it as an editable project with your material.

01 Reference + attachments
A local video file plus your photos, logo, copy and music. The reference is studied, never shipped.
02 Measure
Sections in beats, shot lengths, still frames and beat alignment, measured from the actual file.
03 Rebuild
On the closest template or a new composition. Missing artwork is generated; the result is checked against the reference.
Use the vvv skill to recreate ./reference.mp4 as our own film with the photos in ./photos, our logo and copy. Generate any missing artwork and show me a checked sample before the full render.

Best with an image-capable agent. With Claude Code and Codex both installed, Claude Code can use Codex's image generation through the bundled bridge. Video and voice are not generated. How it works

Also included

Your agent runs the whole thing

You describe the film, watch the sample and say what to change. Setup, scripts, rendering and checks are the agent's job:

01 Pick a template
Matched to your format, style and photo count, such as Album · 9:16 for a phone-first short.
02 Place the photos
Checks their size and orientation, then fills the opening, gallery and ending.
03 Write the copy
Names, date and every line of text, validated before anything renders.
04 Set up and sample
Installs dependencies, fetches the music and renders a sample for you to watch.
05 Check
Measures format, loudness, still frames and beat sync, then reviews the frames.
06 Deliver
The film plus its editable project, so any agent can pick it up later.

The first time your agent runs commands on your machine, it may ask for permission. To run things by hand or build a new template, see getting started and contributing; ready-made .vvv template packages are attached to Releases.

https://github.com/actionow-ai/vvv/blob/HEAD/A row of V letterforms, the front one glowing signal yellow

Make your first film today.

Get started · Website · [email protected] · Linux.do

Status
0.1, an early release. Verified end to end on macOS ARM64 with Claude Code and Codex; WorkBuddy and other platforms are less tested. Verification and limits
License
Code, docs, templates and demo media are MIT. Fonts, preview soundtracks and third-party code keep their own terms: media · third-party notices
Get involved
Contributing · Roadmap · Changelog
Security · Brand kit · Submit a template

© 2026 Vibe Vision Video contributors · vibevision.video

GitHub Stars & Activity

439Stars
124Forks
0Open issues
PythonLanguage

GitHub Popularity

GitHub stars439
Forks124
Open issues0
Primary languagePython
License-
Stars gained today0
Created-
Last pushed-

Trending History

Weekly boardrank #69 · ▲ 0 stars

Related GitHub Projects

1

Motionsites-AI / claude-skill

Python★ 1,021⑂ 106
→
2

deepopen-com / deepopen-3d-webs

Python★ 517⑂ 1
→
3

konlu / story-studio

Python★ 456⑂ 110
→
4

OpenBMB / MiniCPM-OCR

Python★ 417⑂ 26
→
5

patch-gg / anymove

Python★ 400⑂ 41
→
6

MiniMax-AI / mcode-stack

Python★ 370⑂ 25
→
7

toyxyz / toyxyz_RGBMocap

Python★ 274⑂ 41
→
8

brainstormity / LightPost

Python★ 230⑂ 50
→

More Trending Repositories