diffusionstudio/lottie

Generate production-ready Lottie animations with Claude Code or Codex

What it solves

It simplifies the creation of production-ready Lottie animations by allowing users to generate them using text prompts via coding agents, rather than manually designing them in complex motion graphics software.

How it works

The framework acts as a "skill" that can be added to coding agents (such as Claude Code or Codex). When a user provides a prompt—often grounded in SVGs or screenshots—the agent generates the Lottie JSON file. The system includes a player that automatically loads these files from a specific directory, enabling real-time inspection, scrubbing, and refinement as the agent edits the code.

Who it’s for

Developers and designers who want to quickly iterate on vector animations for web, mobile (iOS, Android, React Native), or Flutter applications without needing deep expertise in Lottie's JSON structure or After Effects.

Highlights

  • Agent-driven generation: Works with coding agents to turn text descriptions and SVG paths into animations.
  • Real-time preview: Includes a player that live-updates as the agent modifies the animation files.
  • Multi-platform support: Generated animations are compatible with standard Lottie players across web, iOS, Android, React Native, and Flutter.
  • Professional controls: Supports motion design terminology (easing, camera movements) and custom property controls.

Related

  • Project
    google-labs-code/stitch-skills

    A collection of agent skills and plugins for Google Stitch that enables AI coding agents to automate design generation, design system management, and conversion of designs to frontend code.

  • Project
    OpenVGLab/OmniLottie

    OmniLottie is a multimodal AI generator that creates complex vector Lottie animations from text, image, or video inputs using pre-trained Vision-Language Models.

  • Project
    vibe-motion/skills

    A collection of modular animation and rendering skills for AI agents to generate professional motion graphics, 3D effects, and promotional videos programmatically.

  • Project
    1weiho/open-slide

    A slide framework designed for AI agents that turns natural language descriptions into polished React-based presentations with a built-in feedback loop for iterative editing.

  • Project
    thesysdev/openui

    A full-stack Generative UI framework that uses a compact, streaming-first language to let LLMs render structured, interactive components with high token efficiency.