OpenMotion: recreate and make motion videos with your agent
nexu-io/openmotion
Your AI assistant becomes a video maker. Give it a reference video or an idea, and it builds an editable motion-graphics video. The video opens in a local editor (Studio) where you can change it by hand, and you get an MP4 when you ask. It comes with a local app, five main skills and three optional ones.
Pack description by its author: “Your AI assistant becomes a video maker. Give it a reference video or an idea, and it builds an editable motion-graphics video. The video opens in a local editor (Studio) where you can change it by hand, and you get an MP4 when you ask. It comes with a local app, five main skills and three optional ones.”
Video, images and mediaKnowledge and rules for your assistantGives your assistant new abilities with scripts
1. Changes your files
Skills that write or edit files: openmotion-recreate, openmotion-director, openmotion-template-to-video, openmotion-video-to-template, openmotion-production, openmotion-design-remix, openmotion-presenter-story.
github.com/nexu-io/openmotion/blob/7b4badb/2. Runs code on your machine
Install from source: npm ci downloads locked dependencies and builds Studio; the Codex script also registers a local plugin marketplace and plugin. npm start: Starts a local service and Studio in your browser; it reuses a service for the same workspace or picks a free local port, and keeps running in the background.
github.com/nexu-io/openmotion/blob/7b4badb/3. Sends data
Keep projects and credentials outside the checkout. The install guide asks the agent to open the template library right after install and to fall back to an npm mirror on network errors; check those steps before you let it run.
github.com/nexu-io/openmotion/blob/7b4badb/4. Commercial use
Apache-2.0 for the app and skills; models and third-party libraries keep their own terms
github.com/nexu-io/openmotion/blob/7b4badb/Checked against the pack's files at commit 7b4badb, on Nov 13, 2026. Tap a verdict to see its source.How we checkedReport an error
The pack has changed since AgentGid checked it on Nov 13, 2026. Some details may be out of date.
Good for you if
- You saw a motion video (a product launch, a brand film) and want one like it for your own product
- You want an original explainer, product demo or brand film made from your topic and product material
- You have an editable video template and want your text, logo and colours put into it
- You use Codex, Claude Code, DeepSeek Harness or WorkBuddy, or another assistant that can connect a local MCP server
Probably not for you if
- You need live action, talking heads or AI footage recreated: the recreation workflow covers motion graphics only
- You want only a quick ready video file: the default result is a project open in the editor, and an MP4 only when you ask
- You cannot run Node.js and a local app on your computer: the skills need the OpenMotion app to do the work
What you'll notice
- A local editor (Studio) in your browser with a template library and a timeline
- Your assistant asks at most one batch of questions, then works through to the finished project
- The result opens in the editor; an MP4 file comes only when you ask for it
- Usage data is sent to the makers by default until you switch it off
What you need
- Codex, Claude Code, DeepSeek Harness, WorkBuddy, any agent with local stdio MCP
- Mixed, Apache-2.0 license
- Ask your assistant to follow install.md, or clone the repo and run npm ci, npm run build:studio, npm start
- Free and open source. Generating new images, video, music or voice uses your own Atlas Cloud or fal.ai keys (paid by you), or your Codex login. Rendering needs Chrome/Chromium and FFmpeg.
Words on this page
- Skill
- A set of written instructions your AI assistant follows. Installing one is like giving it a playbook.
- Skill pack
- Several skills in one GitHub repository, installed together.
- MCP
- A standard way to connect an AI assistant to outside tools and data.
- Plugin
- A package your assistant installs that can bring skills, commands and hooks together.
- Repository
- A project folder on GitHub with its files and history.
- CLI
- A program you run by typing commands in a terminal.
| Repository | nexu-io/openmotion · website |
|---|---|
| Also on AgentGid | Openmotion as an agent: usage, releases and alternatives |
| GitHub stars | 9,975 |
| Skills | 12 (12 SKILL.md in the repo, 6 in skills/) · 3 with scripts |
| Category | Video, images and media |
| License | Apache-2.0 |
| Last updated | Nov 15, 2026 · card checked Nov 13, 2026 at commit 7b4badb |
| Install counts | nexu-io/openmotion on skills.sh, Vercel's skills directory, which shows installs and security audits per skill |
nexu-io/openmotion popularity over time
What OpenMotion does
- Five main skills split the work: recreate a reference video, make an original film, fill an editable template, turn a video into a reusable template, and make scoped edits, previews and exports
- The assistant reads your workspace first (README, brand files, logos, screenshots) and uses it as the film's content
- Videos are HTML, CSS and JavaScript scenes; the same project opens in Studio and renders to MP4
- The assistant works through eleven local MCP tools: find templates, create and read projects, edit with a revision check, import media, preview, export, restore versions
- A recreation is exported and measured against the reference frame by frame with a bundled script before delivery
- Motion.md: a Markdown file that records a video's shot order, timing, transitions and replaceable assets
Never cut, per the skill: Facts: the skills tell the assistant not to invent prices, claims or other missing facts, and to say plainly where a result falls short.
From the pack's SKILL.md files, summarised by AgentGid.
The 5 skills, explained
openmotion-recreate
Rebuilds a reference video as your own editable film, with your copy, brand and assets
You give
- A reference video: a link or a local file
- Your product material in the workspace (README, logos, screenshots, brand colours and fonts)
- What should change, if you know: wording, brand, images, pacing, duration
You get
- An editable OpenMotion project, open in the editor
- The reference's soundtrack kept and re-timed, unless you ask for silence
- A short reply: what changed, which assumptions it made, any limit you would notice
openmotion-director
Plans and makes an original motion video on your topic, or reviews one you already have
You give
- Your topic, audience and the one message
- Product facts and material
- Format: where it will be published
You get
- A creative plan and action script, if you ask for the concept only
- A short test clip of the riskiest part before the full film
- The full editable project, open in the editor
openmotion-template-to-video
Makes a video from an editable template, unchanged or with your text, brand and assets
You give
- A template: from the library, a project folder or a ZIP
- Your replacement text, logo and images
You get
- The template open in the editor, unchanged or edited
- Checks recorded in the copy's TEMPLATE.md
- An MP4 only if you ask for a video file
openmotion-video-to-template
Rebuilds a reference video as a template you can fill again and again
You give
- A reference video: a link or a file
You get
- A template folder or ZIP with local assets
- A preview and a cover
- TEMPLATE.md: what can be changed and where it still differs from the original
openmotion-brandkit
Writes a BRANDKIT.md and, if asked, a MOTION_DESIGN.md from your brand material
You give
- Your brief, brand guide, logo files, product screenshots, reference links
You get
- BRANDKIT.md: brand facts, approved wording, logo rules, colours and type, assets with sources, what may change
- MOTION_DESIGN.md when a reusable motion language is needed
- A list of assets, sources and open choices
Its rules, in pictures
Each visual acts out what it does
| In your design | The story it plays |
|---|---|
| A tilted interface | The interface is revealed at a tilt while the camera moves; you change the headline and copy |
| A title through a portal | A wireframe portal with depth and camera timing; you change the title and subtitle |
| A title behind leaves | Leaves sweep across and cover the words, with two holds; you change two headline phrases |
| Code | A code slab is extruded in 3D, or the code assembles from particles; you change the shown function |
| Glass widgets | Glass cards and meters enter one after another; you change labels, units and the feature story |
| A big number | Zoom into one large number, open into a rotating ring of marks, carry the centre mark into the closing frame |
Drawn by AgentGid from the values in the skill's files. This is not output of the skill; sample text is ours.
See it in action
Same task, same model, with and without the skill
Prompt: Ask it to keep the five-second timeline, orbit, sound and logo, change the number to `00:00:15`, and change the caption to “NYT Graph”.
The reference: a five-second excerpt of a launch video that opens on a big number, pulls back to a ring of marks and pairs two marks.
Read the whole answerAn editable 1280×720 HTML composition with the OpenDesign symbol, a rotating ring of nine labels, original sound cues, a Motion.md timing table, a comparison video and a second cut made by changing two fields.
Verbatim output from the author's run, published in examples/reference-reveal/MOTION.md. AgentGid did not run it.
The skill defines what its answer looks like. Its own example:
BRANDKIT.md 1. Brand name, audience, product facts and the message of this video 2. Approved wording, and claims that need evidence before use 3. Logo locations and clear-space / cropping rules 4. Colours, typography and fallbacks (supplied rules vs proposals) 5. Images, screenshots, footage and sound, with sources and permission notes 6. What may change, what must remain, open gaps
When to reach for it
| You want | Use |
|---|---|
| A video like one you saw | openmotion-recreate: give the link or file |
| An original explainer or product film | openmotion-director |
| Only a plan or script first | openmotion-director, asking for the concept only |
| A video from a template in the library | openmotion-template-to-video, or Open and edit in Studio |
| A template you can reuse for many videos | openmotion-video-to-template |
| Small changes or an MP4 of an existing project | openmotion-production |
Skills in nexu-io/openmotion
| Skill | In plain words | Changes files? | What it does (author) |
|---|---|---|---|
| openmotion-director | Plans and makes an original motion video on your topic, or reviews one you already have | Yes | Plan and create original motion videos and motion graphics with OpenMotion. Use for “做一个 motion 视频”、动效视频、动画短片、先构思视频怎么呈现, including esports recaps, explainers, product demos and brand films. Also use for narrative, motion or sound redesign and creative review. Execute established edits/exports with…npx skills add nexu-io/openmotion --skill openmotion-director |
| openmotion-production | Does the routine work on a project you already have: change text, colours or timing, swap music, preview, fix, export | Yes | 执行 OpenMotion 已有工程在既定创作决定下的局部修改、素材或音轨替换、预览、技术排错、导出与交付。重新设计叙事、动作或声画关系使用 openmotion-director;已有模板出片走 openmotion-template-to-video,参考作品复刻走 openmotion-recreate,视频转可复用模板走 openmotion-video-to-template。仓库开发与文档维护不触发影片制作。npx skills add nexu-io/openmotion --skill openmotion-production |
| openmotion-recreate | Rebuilds a reference video as your own editable film, with your copy, brand and assets | Yes | Recreate a reference video (a link or file) as the user's own film with OpenMotion: rebuild it as an editable OpenMotion project and hand it over open in the editor, keeping the original content or swapping in the user's copy, brand and assets. This includes small edits to the user's own finished… has scriptsnpx skills add nexu-io/openmotion --skill openmotion-recreate |
| openmotion-reference-video | — | — | OpenMotion 原生 Hyperframes 编写的兼容入口,供旧引用继续使用。新的视频任务按本轮意图进入相应专业 Skill,工程操作复用 openmotion-production;本入口不承担专门的视频复刻分析。npx skills add nexu-io/openmotion --skill openmotion-reference-video |
| openmotion-template-to-video | Makes a video from an editable template, unchanged or with your text, brand and assets | Yes | Browse, compare and recommend OpenMotion catalog templates with a visible library preview, or make a video from an existing editable template, project folder, ZIP or selected gallery source. Preserve agreed motion and content; resume existing work. Video-only references use openmotion-recreate;…npx skills add nexu-io/openmotion --skill openmotion-template-to-video |
| openmotion-video-to-template | Rebuilds a reference video as a template you can fill again and again | Yes | 使用 OpenMotion 将参考动效视频或链接重建为可反复换内容的可编辑模板,交付源码、素材、预览、编辑说明与文件夹或 ZIP。仅在用户要求可复用模板时使用;按参考制作本次成片走 openmotion-recreate,使用已有模板出片或替换内容走 openmotion-template-to-video,原创走 openmotion-director。npx skills add nexu-io/openmotion --skill openmotion-video-to-template |
| add-byok-provider | — | — | Add or maintain a built-in BYOK media provider in the OpenMotion repository, including official API research, credentials, model discovery, generation adapters, editor configuration, provider references and verification. Use for contributor requests to integrate a supplier; ordinary media…npx skills add nexu-io/openmotion --skill add-byok-provider |
| openmotion-brandkit | Writes a BRANDKIT.md and, if asked, a MOTION_DESIGN.md from your brand material | No | OpenMotion — Prepare a reusable Brandkit and motion-design brief from user-supplied brand facts, assets and references. Use when organizing brand context for a video, not for rendering or editing a project.npx skills add nexu-io/openmotion --skill openmotion-brandkit |
| openmotion-design-remix | Puts your words into one of six ready motion pieces, keeping their timing and movement | Yes | OpenMotion — Adapt one of six bundled motion compositions using its MOTION_DESIGN.md, preserving timing and movement while replacing the user's copy. Use for these source-backed examples or as a concrete pattern for a reusable motion design package. has scriptsnpx skills add nexu-io/openmotion --skill openmotion-design-remix |
| openmotion-presenter-story | Recipes for videos where a person talks to camera, with captions, screen recordings and motion around them | Yes | OpenMotion — Adapt presenter-led videos using reusable motion design recipes for listicles, workflow demonstrations and product walkthroughs. Use with the creator's own footage and measured speech timing to combine spoken storytelling, captions, screen recordings and motion.npx skills add nexu-io/openmotion --skill openmotion-presenter-story |
| openmotion-onboarding | — | — | Welcome the user after OpenMotion plugin setup and open its template library.npx skills add nexu-io/openmotion --skill openmotion-onboarding |
| product-story | — | — | Adapt the Product Story recipe to a supplied product or lesson brief using its visual identity, three-scene rhythm and input limits. Use when the user selects this package or asks to adapt its recipe. has scriptsnpx skills add nexu-io/openmotion --skill product-story |
The author's descriptions come from each skill's SKILL.md; the plain-words column is AgentGid's.
Good to know before you install
- It is a whole local app, not only text files. The skills need the OpenMotion app (MCP server, Studio, renderer); installing the skills alone does not install it.
- Usage data is sent to the makers' PostHog project by default. Turn it off in Studio (Privacy settings → Share usage data) or with OPENMOTION_TELEMETRY=0 or DO_NOT_TRACK=1.
- A background service keeps running after you close the launcher.
- Generating new media (images, video, music, voice) is billed to your own provider accounts; using your own footage needs no media API.
- Keep your projects and keys outside the checkout; MOTION_DATA_DIR sets where projects live.
- Reference videos from other brands are only for study: the templates and remix pieces keep some upstream artwork, and third-party media keep their own licenses.
Before you start
Works in
- Codex: plugin (skills + MCP)
- Claude Code: MCP server + skills folder
- DeepSeek Harness: plugin bundle
- WorkBuddy: MCP server
- Other clients with local stdio MCP: MCP server
- Any agent with a skills folder: skills CLI (instructions only)
You will need
- Node.js 22.18+ with npm: Runs the app and MCP server
- Chrome/Chromium, FFmpeg and FFprobe: Preview
- Atlas Cloud or fal.ai API key (optional): Only to generate new images
- Git: Source install
Steps only you can do
- Add your Atlas Cloud or fal.ai API key in Studio's Model Settings (only to generate new images, video, music or voice) (Studio → Model Settings)
Then: The agent and Studio can generate media through the Model Gateway and place it in the project - Decide on usage data: switch off Share usage data in Studio Privacy settings, or set OPENMOTION_TELEMETRY=0 (Studio → Privacy settings, or tracking/README.md)
Then: No usage events leave the machine - Pick a template in the library before the agent creates a project (Studio → Template library)
Then: The agent creates or continues that one project
Mistakes to avoid
Install only the skills with npx skills add and expect videos
Also install and connect the OpenMotion app (source setup or the local installer)
The skills CLI copies instructions only; the work runs through the app's MCP tools and rendererAsk it to recreate a talking-head or live-action video
Use it for motion graphics; put your own footage into a motion-graphics adaptation
The recreation workflow covers motion graphics onlyFollow docs/install.md from the source repository as a ready install guide
Use install.md (source) or the README's agent setup; docs/install.md is a template for published packages
In the repo its package name and version are placeholdersPoint Studio and the MCP server at different data folders
Use one MOTION_DATA_DIR for both
Otherwise the agent and the editor see different projectsAsk for changes while turning a reference into a template
Get the faithful template first, then change it with openmotion-template-to-video
video-to-template does not mix requested changes into the rebuild
Which one to pick
| If you need | Pick |
|---|---|
| You want a reference video recreated with your brand, a local editor with a timeline and agent-led edits | This pack |
| You only need the HTML-to-MP4 engine and its agent skills, without a studio app | heygen-com/hyperframes |
| You prefer React and Remotion for editable product promos | Vincentwei1021/video-shotcraft |
| You want script, AI voiceover, music and clips rendered with Claude Code on open-source models | digitalsamba/claude-code-video-toolkit |
Works well with
- openai-codex: The repo ships a Codex plugin manifest and an install script for Codex
- claude-code: The local installer registers the MCP server and skills for Claude Code
- hyperframes: Projects are native HyperFrames compositions rendered by its pinned CLI
- ffmpeg: Export, checks and the frame measurer use FFmpeg and ffprobe
May I use it like this?
| Use | Answer | Condition |
|---|---|---|
| In a commercial app | Yes | Apache-2.0 for the app and skills; models and third-party libraries keep their own terms |
| Passing the files on | With conditions | Apache-2.0: keep LICENSE and NOTICE files; third-party templates, media and fonts keep their own licenses |
| Work for clients | With conditions | Use your own or licensed assets; reference brands' artwork is not yours to ship |
What leaves your machine
- Usage events with app version, environment and a random installation ID; GeoIP is on in the default config → PostHog (us.i.posthog.com), the makers' project, While the app or MCP server runs, by default. Opt out: Studio Privacy settings → Share usage data, or OPENMOTION_TELEMETRY=0 / DO_NOT_TRACK=1
- Prompts and input media for generation jobs → Atlas Cloud or fal.ai, Only when you generate media with a provider key set. Opt out: Use your own footage, images and audio, or the local Codex image path
- Download requests for dependencies, Chromium, FFmpeg/ffprobe and the online template catalog → npm registry, storage.googleapis.com, ffmpeg.martin-riedl.de, nodejs.org, the makers' catalog, At install and first render. Opt out: Point the HYPERFRAMES_* variables at local Chromium and FFmpeg; use a source checkout for local templates
Install OpenMotion
Official commands from the repository
Read https://github.com/nexu-io/openmotion/blob/main/install.md and follow the instructions to install and connect OpenMotion in the current agent.
A prompt you paste into your agent. It clones main, runs npm ci, builds Studio, starts the app and connects MCP. Read install.md first.
git clone --depth 1 https://github.com/nexu-io/openmotion.git cd openmotion npm ci npm run build:studio npm start
Open the studioUrl or previewUrl it prints, then Template library.
bash scripts/install-motion.command
Run from a normal terminal. Registers a local marketplace (openmotion-local) and the openmotion plugin, which loads skills/ and .mcp.json.
Select --host claude in the local installer, then run /mcp in Claude Code to check the connection.
Add an mcpServers entry named openmotion that runs node --experimental-strip-types /absolute/openmotion/mcp.ts with MOTION_DATA_DIR set.
npx skills add ./skills --skill openmotion-director openmotion-production openmotion-template-to-video openmotion-recreate openmotion-video-to-template
Copies the instructions only; connect the app separately. Optional library skills install the same way from ./library/skills.
Or with the open-source skills CLI: npx skills add nexu-io/openmotion. Skills are instructions your agent follows: read them before installing.
What it installs and runs on your machine
Read in the code at commit 7b4badb, Nov 13, 2026
| When | What happens |
|---|---|
| Install from source | npm ci downloads locked dependencies and builds Studio; the Codex script also registers a local plugin marketplace and plugin. |
| npm start | Starts a local service and Studio in your browser; it reuses a service for the same workspace or picks a free local port, and keeps running in the background. |
| Agent session | The agent host starts the local MCP server (node mcp.ts) over stdio; edits go through revision checks. |
| Preview and export | Renders HTML scenes with Chromium and encodes with FFmpeg/FFprobe. The npm setup downloads Chromium, FFmpeg and ffprobe in a background worker. |
| Recreation check | The bundled measure_frame.mjs runs ffmpeg/ffprobe locally to compare frames; it has no npm dependencies. |
| Media generation (only if you set it up) | Sends requests to Atlas Cloud or fal.ai with your keys, or runs your local Codex CLI for images; results are saved into the project. |
| Always (default on) | Usage events go to PostHog (us.i.posthog.com) with a random installation ID stored in the data directory. |
| Template library | The npm app uses an online template catalog; a source checkout reads templates from the checkout. |
Settings
MOTION_DATA_DIR: Where projects and app data live; Studio and MCP must use the same oneOPENMOTION_TELEMETRY / DO_NOT_TRACK: OPENMOTION_TELEMETRY=0 or DO_NOT_TRACK=1 switches usage data offHYPERFRAMES_BROWSER_PATH, HYPERFRAMES_FFMPEG_PATH, HYPERFRAMES_FFPROBE_PATH, FFMPEG_PATH, FFPROBE_PATH: Point the renderer to your own Chromium and FFmpegOPENMOTION_POSTHOG_HOST / OPENMOTION_POSTHOG_KEY: Send usage data to your own collector instead
Quick answers
- Is it free?
- The app is free and open source under Apache-2.0. Image, video, music and voice generation are billed by the providers you connect.
- Can it recreate a talking-head or live-action video?
- No. The recreation workflow covers motion graphics only; your own footage can go into a motion-graphics adaptation.
- Do I get an MP4?
- Only when you ask. The project open in the editor is the deliverable; the recreation workflow exports internally to check the result.
- Does it send data anywhere?
- Yes, usage events go to PostHog by default (switch off in Privacy settings or with OPENMOTION_TELEMETRY=0), and media generation sends requests to the providers you set up.
- Which Node.js version?
- The app needs Node.js 22.18 or later; source validation is pinned to Node.js 26.11.1.
Checked by AgentGid on Nov 13, 2026 against commit 7b4badb of the pack's own files. Related: heygen-com/hyperframes, vercel-labs/skills, nexu-io/open-design. agent.md for AI agents · Report a mistake
More video, images and media skill packs
| # | Skill pack | Skills | GitHub stars | Updated |
|---|---|---|---|---|
| 1 |
OpenMontageInc/OpenMontage Your AI coding assistant becomes a small video studio. You describe a video in plain words; it researches the topic, writes the s…
|
92 | 80.6K | 2026-11-09 |
| 2 |
emilkowalski/skills Fifteen design playbooks for your AI assistant, most of them about animation. It builds animations with set speeds and curves, sa…
|
19 | 57K | 2026-11-13 |
| 3 |
latent-spaces/brag Your AI assistant turns a project you built into a 15 to 25 second launch video. It reads your project, writes a plan and a story…
|
2 | 21.5K | 2026-10-23 |
| 4 |
Vincentwei1021/video-shotcraft Your AI assistant turns your website or app into a short promo film. It screenshots your real pages and picks camera moves from a…
|
1 | 19.8K | 2026-11-11 |
| 5 |
greensock/gsap-skills Eight reference guides from the makers of GSAP, a JavaScript library for animating websites. Your assistant learns how to write G…
|
8 | 18.5K | 2026-07-29 |
| 6 |
lemomo-ai/lemo-opuscar A toolbox of film styles made in code for Claude Code: 99 ready to use, and your own. Each style is a style prompt plus a demo fi…
|
1 | 16.4K | 2026-11-12 |