awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
oso95 avatar

oso95/scroll-world

0
View on GitHub↗

Scroll World

Scroll-world is an AI agent skill that turns a brand brief into a scroll-driven landing page, where scrolling moves a camera through a small set of connected, AI-generated scenes without cuts. It ships as a self-contained folder of instructions and assets that an agent loads as a plugin, through a skills tool, or by copying the folder manually. The agent interviews the user for the subject, pitch, brand kit, art direction, ordered scenes, mobile support, and budget, then works through the build in stages.

The pipeline runs from the brief to scene stills, then to connector clips, then to the finished page, pausing for approval between stages. Each camera-flight clip is generated from the actual rendered frames of its neighboring scenes, so the seams between clips match exactly. Costs for image and video generation are estimated up front and checked against the live account balance, and nothing is generated until the user approves. Scene stills can come from either a hosted credit-based service or a locally installed command-line tool.

On the page itself, a config-driven engine maps scroll position to playback time across the chained clip sequence. One declarative configuration describes scenes, clips, and timing, and the engine works in plain HTML or common web frameworks. A second chain of clips can be rendered natively in portrait orientation and is swapped in automatically on phone-sized screens, rather than cropping the landscape version.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Features

  • Landing Page & Dashboard Generators - Generates immersive landing pages from a brand brief where scrolling flies a camera through connected AI-generated scenes.
  • Interactive Motion Landing Pages - Generates an immersive landing page where scrolling moves a camera through connected AI-generated scenes without cuts as one continuous journey.
  • Skill Packaging - Ships as a self-contained folder of instructions and assets that an agent loads as a plugin, through a skills tool, or by manual copy.
  • AI Agent Skills - Packages a reusable, guided agent workflow as a folder of instructions and assets that an AI coding agent loads to build a finished page.
  • Staged Approval Workflows - Pauses the agent workflow for user approval between brief, stills, connector clips and final page before costly generation proceeds.
  • Image-to-Video Generation - Animates scene stills into camera-flight clips using the rendered frames of neighboring scenes as start and end references so seams match exactly.
  • Scroll-Scrubbed Frame Seeking - Ships a config-driven engine that maps scroll position to playback time across a chained clip sequence, in plain HTML or common frameworks.
  • Scroll-Driven Page Timelines - Builds landing pages where scroll position drives video playback along one timeline, moving a camera through connected scenes without cuts.
  • Image Generation Backends - Selects scene-still generation between a hosted credit-based service and a locally installed command-line tool behind a common interface.
  • Generation Spend Estimators - Estimates credit or dollar cost of image and video generation and confirms it against the live account balance before spending.
  • Media Generation Cost Gates - Estimates image and video generation costs up front, checks them against the live account balance, and generates nothing until the user approves.
  • AI Scene Still Generators - Creates cohesive stylized stills for each scene with an image model, from a hosted credit service or a local command-line tool.
  • Camera Flight Clip Generators - Produces image-to-video clips for each scene and connector clips between neighbors, built from rendered frames so every seam matches.
  • Scene and Prop Art Settings - Generates cohesive stylized stills for each scene with an image model, keeping environments consistent before they are animated into flight clips.
  • Frame-Controlled Generators - Creates connector clips constrained by the real end and start frames of adjacent scenes so seams between clips match exactly.
  • Portrait Video Experiences - Renders a second clip chain natively in portrait and swaps it in automatically on phone-sized screens rather than cropping the landscape version.
  • Brand Storytelling Websites - Turns a brand's pitch, art direction and ordered scenes into a cinematic single-page site presented as a small explorable world.
  • Brief-to-Video Render Pipelines - Runs the build in fixed order from brand brief to scene stills, connector clips and the finished scroll page.
  • Declarative Video Scrub Engines - Ships an engine that reads one declarative config of scenes, clips and timing to drive scroll-linked playback in plain HTML or common frameworks.
10,865 stars·1,185 forks·JavaScript·MIT·3 views

Star history

Star history chart for oso95/scroll-worldStar history chart for oso95/scroll-world

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Frequently asked questions

What does oso95/scroll-world do?

Scroll-world is an AI agent skill that turns a brand brief into a scroll-driven landing page, where scrolling moves a camera through a small set of connected, AI-generated scenes without cuts. It ships as a self-contained folder of instructions and assets that an agent loads as a plugin, through a skills tool, or by copying the folder manually. The agent interviews the user for the subject, pitch, brand kit, art direction, ordered scenes, mobile support, and budget, then…

What are the main features of oso95/scroll-world?

The main features of oso95/scroll-world are: Landing Page & Dashboard Generators, Interactive Motion Landing Pages, Skill Packaging, AI Agent Skills, Staged Approval Workflows, Image-to-Video Generation, Scroll-Scrubbed Frame Seeking, Scroll-Driven Page Timelines.

Which projects share features with oso95/scroll-world?

Projects with overlapping indexed features include: rlaope/oh-my-hermes — Oh My Hermes (Hermes Orchestrator) is a workflow layer that sits on top of the Hermes agent runtime. It routes… ningzimu/codex-ppt-skill — This is a skill for AI coding agents that turns articles, reports, papers, notes, Markdown, PDF, or Word files into a… feitangyuan/onetake — Onetake is a skill for AI coding agents that produces product launch films, teasers, and feature demos as a single… opensquilla/opensquilla — OpenSquilla is an LLM agent orchestration framework designed to coordinate multi-step AI workflows and tool execution… nateherkai/scroll-craft — Scroll-craft is a packaged skill for coding agents such as Codex and Claude Code, and it can also be installed as a… jetbrains/go-modern-guidelines — This project is a skill and plugin package that gives AI coding agents a curated set of guidelines for writing…

Projects sharing features with Scroll World

These projects share indexed features with Scroll World. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • rlaope/oh-my-hermesrlaope avatar

    rlaope/oh-my-hermes

    5,229View on GitHub↗

    Oh My Hermes (Hermes Orchestrator) is a workflow layer that sits on top of the Hermes agent runtime. It routes requests to staged skills, external coding executors, and verification gates, through chat or a terminal interface. Completion is evidence-gated: every status carries a stage and confidence, and work is marked verified only after tests, reviews, or CI checks have actually passed. It is also distributed as a catalog of installable workflow skills and plugin hooks, for Hermes and other coding-agent hosts. Its main focus is multi-agent coding delegation. Scoped tasks are handed to codin

    Pythonagentaiai-agent
    View on GitHub↗5,229
  • ningzimu/codex-ppt-skillningzimu avatar

    ningzimu/codex-ppt-skill

    7,712View on GitHub↗

    This is a skill for AI coding agents that turns articles, reports, papers, notes, Markdown, PDF, or Word files into a complete slide deck. It plans an outline and visual style, renders every slide as a full widescreen image, and assembles those images into a single PowerPoint file. Because each page is an image rather than a set of text and shape layers, slides are not built as editable text boxes. A speech script is written for the deck and embedded in each slide's notes area during assembly. The workflow is staged. The user approves the outline, page count, key points, visual style, image m

    Pythonagent-skillsai-pptclaude-code
    View on GitHub↗7,712
  • feitangyuan/onetakefeitangyuan avatar

    feitangyuan/onetake

    3,918View on GitHub↗

    Onetake is a skill for AI coding agents that produces product launch films, teasers, and feature demos as a single continuous take. It installs by cloning into an agent's skills folder, after which plain-language requests can trigger the whole workflow of planning, building, and rendering. Each beat in the film grows out of the previous element instead of replacing it, so scenes flow together rather than reading as slides. What sets it apart is how it plans and checks that continuity. It can break a reference film down into measurable data such as stillness, cut positions, and motion easing,

    Pythonagent-skillanimationcanvas
    View on GitHub↗3,918
  • opensquilla/opensquillaopensquilla avatar

    opensquilla/opensquilla

    4,211View on GitHub↗

    OpenSquilla is an LLM agent orchestration framework designed to coordinate multi-step AI workflows and tool execution using directed acyclic graphs. It functions as a centralized system for managing specialized skill packages and executing complex reasoning sequences. The project distinguishes itself through a routing gateway that directs tasks to different AI providers based on complexity, cost, and performance. It utilizes a multi-tier AI memory system that organizes working, episodic, and semantic knowledge using local embeddings and SQLite, alongside a secure execution sandbox that isolat

    Pythonagentaiai-agents
    View on GitHub↗4,211
Compare all 30 related projects→