Creative · Design

ResearchStudio packages the entire research lifecycle—from half-baked direction to published deliverables—as agentic skills for Claude Code and Codex.

A self-hostable infinite canvas that wires AI image generation, reference editing, and chat into one collaborative workspace.

One desktop UI that wires together ComfyUI, OpenAI, Gemini, ModelScope, and a dozen other generative APIs—plus some very opinionated legal terms.

huashu-design is an agent skill that converts a brief sentence into a finished HTML prototype, MP4 animation, or editable PowerPoint.

A Codex skill that turns documents into image-based PowerPoint decks via gpt-image-2, with enough guardrails to keep the agent from going off the rails.

This unofficial rebuild of a Google Research project chains specialized agents to turn rough text and data into publication-ready academic figures.

A gallery of copy-paste CSS transitions that doubles as an installable AI skill and a live motion-tuning panel for your running app.

LocalMiniDrama wires your API keys into a Vue+Electron pipeline that turns story outlines into short-form AI video without shipping data to anyone else's cloud.

It turns your existing local AI coding agent into a graphic designer, converting raw notes into ship-ready HTML pages and social cards without asking for an API key.

It generates editable HTML presentations from a simple prompt so you can skip PowerPoint's formatting maze.

Built because Figma keeps locking out developers who want to script their own design files.

An open-source vector design tool that turns text prompts into live UI by orchestrating concurrent AI agents to draw, refine, and export code.

Toonflow exists to turn a manuscript into an animated short drama without juggling five different browser tabs.

Turns raw notes into structured, hand-drawn Chinese tech explainer pages—PNG output, not PowerPoint.

Beav is a desktop-native AI workbench that plugs into every step of the Xiaohongshu influencer pipeline, from scraping competitors to generating covers and video clips.

Most AI writing tools die after three paragraphs; this one treats novel creation as a structured production workflow with agents, memory, and style control.

An AI-native presentation app that generates styled slide decks from a prompt or document and lets you refine them with natural-language commands instead of menu diving.

It exists to turn a chatbot into a novelist by forcing it through a draft-audit-revise pipeline with human approval gates.

It exists to rebuild objects from reference photos as token-efficient, animation-ready Three.js code, using agent vision to gate quality before every sculpting pass.

PenEcho exists because translating a half-formed diagram into a chat prompt is a waste of keystrokes.