Choose theme
AI Visuals
Papermorph
Papermorph is a coding-agent skill for making animated, narrated web books from textbook PDFs or stories.
Its lesson workflow combines moving diagrams, spoken explanations and questions. A separate picture-book workflow builds paper-puppet films with characters, sets, voices and sound. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
An authoring skill and a web player
The skill guides a coding agent through planning, narration, storyboarding, animation and review. The separate player runs the resulting chapters as static web pages.
Why it stands out
Questions inside the explanation
Lesson steps can pause for a learner to answer before continuing. The authoring guide includes activities such as placing a point on a coordinate plane or filling numbers into an expression.
Availability
Public source and example books
The repository provides the skill, engine, scripts and example-book files, and links to an online bookshelf. It declares MIT licensing, with a separate notice for bundled MathJax.
Why it matters
What makes it useful
A textbook explanation may depend on seeing what changes at each step. Papermorph plans chapters as short beats: one idea, its narration and the actions that illustrate it. The authoring guide uses named marks in the narration to time those actions to spoken words. For a maths lesson, this lets the author plan when a label, number or diagram changes as the explanation reaches it. The generated content still needs checking by someone who understands the subject.
What to know
Where it fits
This is a production workflow around a coding agent, rather than a PDF reader. The documented installation targets Claude Code. You choose a pilot chapter and agree a style before producing the rest; those choices are saved in style.json. The build needs uv, FFmpeg and Playwright browsers. Narration can use online Edge TTS or local Kokoro; painted picture-book sets need an image-model API key. The coding model has its own access and usage costs.
Notable points
What stands out
The output format changes what learners can do. A web chapter keeps the player and questions, and ordinary static-book reading progress is stored in the browser. The MP4 export produces a video and a separate SRT caption file, leaving question beats out and directing lesson viewers back to the interactive version. Optional SCORM packaging serves a learning-management system and uses its progress records. These are different delivery choices, not interchangeable copies of every interaction.
Before using
What to review
Start with one chapter and review its explanation, calculations, answer feedback and animation together. The project describes visual and automated checks; those do not establish educational accuracy or learning outcomes.
Separate authoring from delivery when considering data access. A static output folder does not make generation offline: your coding agent and chosen speech or image services may process material. Review those services before using private documents.
The repository is changing quickly. Inspect the current setup and engine instructions before starting a larger book; LifeHubber has not run the generation or export workflow.
Reader fit
Who may find it relevant
Educators, technical learning designers and developers making explanatory media are the clearest audience. Someone exploring the idea can start with the linked bookshelf; making a book requires comfort with a coding agent, local tools and reviewing generated files. For a story project, inspect the picture-book instructions too: its script, scenes, puppets and sound follow a different authoring path from textbook lessons.
Editorial note
Why LifeHubber lists it
LifeHubber lists Papermorph because it connects an explanation to something the learner can do with the picture. A coordinate-plane question, for example, can ask for a point in the diagram instead of only offering a spoken recap. For an educator considering animated course material, this makes the project worth exploring as a way to combine demonstration and practice in one authored lesson. The useful idea is the relationship between the animation and the learner's response; attractive motion alone would not provide that practice.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
More in AI Agents
Keep browsing this category
Explore more AI agent projects.
Paperclip
paperclipai/paperclip
A self-hosted server and dashboard for coordinating agent teams through companies, goals, roles, issues, heartbeats, budgets, approvals, and persistent activity records.
llama-swap
mostlygeek/llama-swap
A local model-server proxy with on-demand loading, groups or matrix rules for model coexistence, idle unloading and a browser interface.
Auto-Company
MaxMiksa/Auto-Company
A continuous local AI-agent loop that uses Claude Code or Codex CLI to coordinate 14 business and engineering roles, carry decisions through one shared consensus file, and expose runs through a local dashboard.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
