Image, video & design

Design & UI agents

Design and UI agents turn plain language into finished design work: open-design runs a local-first workspace for prototypes, dashboards, and motion, while drawio-skill converts code, schemas, and API specs into editable draw.io diagrams. They differ in output you can keep working in, such as editable files, reusable design systems, and tested diagrams rather than flat images.

465 agents · most starred first

Top 100 of 465

open-design★ 108,617

The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Share work, exchange feedback, and iterate together in one workspace.

tldraw★ 51,511

Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.

astryx★ 31,185

An open source design system that's fully customizable and agent ready

huashu-design★ 29,942

Huashu Design 3.0 · 在 agent 里打一句话,拿回能交付的设计:网页 / App 原型 / 可编辑 PPTX / 动画 / 信息图 · 六个候选挑三个方向 · 84 种带样张的风格库 · 越用越懂你的外观账本与设计体检 · HTML-native design skill for Claude Code, Codex, Cursor & any agent

anatomy★ 28,339

An agent skill for creating detailed, interactive isometric illustrations of real-world machines and complex systems. Generates polished SVGs with optional WebGL shaders and 3D effects.

astryx★ 13,758

An open source design system that's fully customizable and agent ready

fireworks-tech-graph★ 12,033

Generate production-quality SVG+PNG technical diagrams from natural language. 7 styles, UML support, and AI/Agent workflow patterns.

drawio-skill★ 10,880

Agent skill that turns natural language, code, Terraform/K8s, SQL, OpenAPI, AsyncAPI, Protobuf and GraphQL sources into editable, tested draw.io architecture diagrams: incremental sync, multi-view projection, drift diff, CI architecture tests, whiteboard derasterize, interactive HTML/PPTX/Mermaid exports.

open-codesign★ 8,245

Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT.

app-store-screenshots★ 7,998

end to end app store screenshot creation using AI

visuallyjs★ 7,766

VisuallyJs releases and issue tracking

superdesign★ 7,630

AI Product Design Agent - Open Source

logo-design-skill★ 7,392

A comprehensive logo-design skill for Claude, Gemini CLI, Codex and other AI agents: principles, process, SVG craft, testing tools and a 1,400+ logo reference library.

openpencil★ 7,304

The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A modern alternative to Pencil.

ip-as-logo-skill★ 6,650

A compact Agent Skill for highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos.

transitions.dev★ 6,425

UI motion agent, a library of 43+ crafted transitions, a skill that fits your workflow.

baoyu-design★ 6,417

Run Claude Design locally as an Agent Skill — Cursor, Codex, DeepSeek Harness & more. Produce polished UI mockups, prototypes, decks & wireframes as self-contained HTML, without claude.ai/design. Best with Opus or Claude.

agentation★ 5,459

The visual feedback tool for agents.

make-interfaces-feel-better★ 4,189

An agent skill that helps make your interface feel better.

thinking-orbs★ 4,053

Dotted thought-orb loading indicators for AI & agent UIs, 9 tuned types, two sizes, auto dark/light

britecharts★ 3,723

Finished, accessible charts that any page, and any agent, can add with one script tag or one validated JSON config.

motion-design-skill★ 3,441

Universal motion design principles for AI agents — timing, easing, choreography, and Disney animation principles adapted for UI

designer-skills★ 3,438

Designer Skills Collection: agentic skills, commands, and plugins for design — from research to systems, UI, interaction, and delivery.

webgradients★ 2,505

180 free CSS3, Figma, Sketch & PSD gradients — plus a JSON dataset for design tools, generators, and AI agents.

paperbanana★ 2,491

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

solid-glass★ 2,394

A design system for AI applications. Material, physical, tactile, technical.

ui★ 2,335

ElevenLabs UI is a component library and custom registry built on top of shadcn/ui to help you build multimodal agents faster.

lobe-ui★ 2,276

🍭 Lobe UI - an open-source UI component library for building AIGC web apps

doop★ 2,188

The open-source alternative to Paper.design. A multiplayer design canvas where humans and AI agents design together, live. MCP built in.

Pretty-mermaid-skills★ 1,591

AI Agent Skill to generate and render beautiful Mermaid diagrams as SVG or terminal ASCII — 15 themes, 6 diagram types, batch CLI, no browser.

AGenUI★ 1,245

Native A2UI Renderer for iOS/Android/HarmonyOS. High performance streaming Generative UI. Custom Components, Styles and more.

boardui★ 1,239

React design system for agentic interfaces. Every free BoardUI component as source, with a working AI chat app on your own model key as the homepage.

open-design-agent-kit★ 1,161

Make posters, social posts, slides and landing pages in the coding agent or chat you already use (Copilot, Claude, Codex, Cursor), with 198 design systems, checks and PDF/PNG/PowerPoint export.

motion-anything★ 1,111

✨ The agentic motion layer — an open-source, chat-native motion engine. Describe the feeling; your AI ships the animation.

claude-motion★ 1,015

A motion design toolkit for coding agents.

openflowkit★ 1,001

Free, open-source diagram canvas. Draw it, write it as code (Mermaid, D2, Structurizr in), ask any AI model or a local one, let Claude Code edit it live over MCP, or map a GitHub repo with every arrow cited to a file and line. MIT, local-first, no account.

ai-draw★ 989

Create and edit drawings through conversation.

typeui★ 967

Design skills and UI prompts for agentic tools such as Claude Design, Google Stitch, Codex, Cursor, and other AI tools

affectui★ 906

UI for AI agents. React components for what agents do – agent trees, tool calls, traces, handoffs and approvals – and for the rest of your app. One file each, install with shadcn or via MCP. Free and open source.

generative-ui★ 898

Generative UI examples for: AG-UI, A2UI/Open-JSON-UI, and MCP Apps.

awesome-design-md-jp★ 815

日本語UIをAIエージェントに正しくつくらせるためのDESIGN.md集。Japanese DESIGN.md collection for AI agents — extending Google Stitch format with CJK typography.

Storyboard-Copilot★ 722

分镜助手 - 基于节点画布的 AI 分镜工作台,一站式完成图片生成、编辑与分镜流程

drawio-ai-kit★ 674

Teach your AI to draw correct, beautiful draw.io diagrams — declarative layout engine, ground-truth stencils, structural validator, vision self-check. AWS · Azure · GCP · Databricks · BPMN. Zero dependencies.

design-agent★ 656

Open-source design agent: on-brand stills, decks, diagrams, charts and motion graphics from a chat thread, built on Deep Agents.

awesome-ios-design-md★ 650

200 production-grade DESIGN.md design systems for the world's best apps. Framework-neutral plus SwiftUI, Jetpack Compose, and Expo. Hand one to your AI agent, ship pixel-matched UI.

figma-use★ 616

Control Figma from the command line. Full read/write access for AI agents — create shapes, text, components, set styles, export images. 100+ commands.

TapCanvas★ 578

TapCanvas — 无限画布 ❌,沉浸式画布 ✅。线上版功能基本对齐TOP级别。agents-cli 智能体蒸馏自 Claude code + codex + hermes-agent。 可使用 cli 工具直接调试 & 调用画布全部功能。

FigMirror★ 574

An Automated AI Agent Tool for Plotting Your Data in Any Paper's Figure Style.

guizang-yingzao-skill★ 540

🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-directed editorial posters with GPT Image. 中国古建筑与在地文化照片 → 艺术指导海报

official-design-md★ 534

Official DESIGN.md files published by companies themselves. First-party design systems that AI agents read to generate consistent UI.

Editable-Design★ 496

Agent-driven creation of editable, tastefully crafted visual artifacts.

EpicInfographics★ 494

A simple skill that will make your Agent create beautiful Infographics

sideshow★ 492

The missing visual surface companion for agents - generate UI mockups, data visualizations, code explainers, and more

deepseek-whalechan★ 492

Keep Whale-chan consistently vivid in every generation: High-consistency character design specification, visual asset library, and agent creation suite.

Open-AI-Design-Agent★ 488

Open-source AI design agent — alternative to Lovart AI, Runway Agent, Luma Labs Agent, Krea Agent, Pika Agent, Galileo AI, Magic Patterns. Autonomous multi-step creative for posters, social, brand kits, ad creatives, and video. Free, MIT-licensed, self-hosted.

visualise★ 488

Agent skill for rendering inline interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — in agent conversations.

awesome-design-md★ 487

55个精选网站设计系统 DESIGN.md,可给AI Agent使用生成匹配UI

agentscope-spark-design★ 470

AgentScope Spark Design - UI Component Library for Alibaba Cloud Apsara Lab

AIA-Academic-Illustrator-★ 468

An AI agent that automates the creation of CVPR/NeurIPS standard academic diagrams. Implements a strict "Logic (Architect) -> Vision (Renderer)" workflow to transform paper abstracts into high-fidelity scientific illustrations.

JarvisHub★ 456

JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents

CharDesk★ 434

A Unicode canvas for humans and AI. Draw diagrams, interfaces, and slides as editable text.

drawio-diagram-builder★ 421

Portable agent skill for research-style editable draw.io diagrams and screenshot-driven refinement

material-design-3-ui-skill★ 382

A reusable Agent Skill for designing, reviewing, and implementing UI/UX with Google Material Design 3, Material You, M3 Expressive, accessibility, adaptive layouts, and semantic design tokens.

smart-drawio-next★ 367

Editable Draw.io diagrams for research and architecture: Next.js web app, Agent Skill, and local MCP server.

refero_skill★ 357

Research-first design skill for AI agents. 150K+ real app screens and flows via Refero MCP.

ichartjs★ 352

An agent-first, JSON-driven visualization runtime for interactive charts, project views, and process diagrams with Canvas and SVG support.

EvoPresent★ 348

[ICLR2026] Official codebase for the paper "Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations"

Loomic★ 323

Open-source AI canvas design agent — alternative to Lovart / CapCut Video Studio / Canva AI. Chat-driven image & video generation on an infinite canvas.

excalidraw-cli★ 322

Generate editable Excalidraw diagrams from text or JSON for agents and developer workflows

diagram-gpt★ 318

Draw flowchart, sequence diagram, class diagram, user journey, gantt, C4C diagram with nature language.

tufte-vdqi-plugin★ 313

Give your AI agents the skill of visualizing data the way Edward Tufte intended.

flowgpt★ 302

Generate diagram with AI

ThinkingOrbs★ 299

Dotted, honestly-3D loading indicators for AI and agent interfaces in SwiftUI. Nine hand-tuned designs, two tuned sizes.

extract-design-system★ 292

Extract design tokens (colors, typography, spacing, border radius, shadows) from any public website. Generates JSON and CSS custom properties for local projects. Available as an AI agent skill (Claude, Cursor, Codex) and standalone CLI.

intent★ 268

Design with Intent: A collection of specialized AI agents and skills for experience design and strategy.

designpowers★ 260

An agent design team you control: 10 agents that run an inclusive design process while you direct.

AutoDesign★ 259

The open-source design agent and harness, better than Claude Design on academic communication artifacts production. This DesignHarness can also be used with any coding harness you like ( Codex/Claude Code/Kimi Code/Pi/OpenCode etc..) and any agentic model you want.

shots★ 252

Claude Code/Agent Skill for making App Store screenshots with GPT Image 2 that you can upload. Give it your App Store link & screenshots of your app and it will produce beautiful app store screenshots ready to upload to Apple (or Google)

uSpec★ 251

Generate design system documentation for your UI components, directly from your AI agent. Renders into Figma or a portable .md file. Works with Cursor, Claude Code, and Codex.

anydesign★ 249

Claude skill that analyzes images, websites, and Figma files and generates a structured design.md with token system, component inventory, and reconstruction notes.

drawio2go★ 239

A modern DrawIO editor application. AI-Powered, Human-AI Collaboration | AI 加持,人机共绘drawio

design-taste★ 229

24 open-source agent skills that turn taste into instructions — ten genre identities, each proven by a same-brief before/after demo

gaia-ui★ 225

Beautifully designed components for building AI Agents 🌎

oil-cover★ 223

为小红书 AI 工具实操内容生成稳定、干净、精致封面的 Claude / Codex Skill(脚本模式 + Agent 自主执行)

agentic-ui★ 215
CanvasAnvil★ 215

CanvasAnvil is an open source AI diagram maker and flowchart generator - an infinite-canvas diagram editor and self-hosted drawio alternative that writes editable .drawio files. Text to diagram, then fix nodes, layout and labels in place. Also AI presentations, interior design CAD/BOM, posters and infographics.

dashmotion★ 204

Animated technical diagrams from plain English or Mermaid — a Claude skill, self-contained HTML/SVG.

OJO-Design-Skills★ 194

Reusable UI/UX design skills for AI coding agents — Codex, Claude Code, ZCode, and more.

OpenDesigner★ 194

A free, open-source add-on for Claude, ChatGPT, Codex and Cursor that turns a few plain answers into a design system, so everything you build looks like it belongs together.

design-buddy★ 189

Design Buddy: visual production Agent Skills for brand design systems, GPT-image-2 images, diagrams, infographics, logos, slide decks, WeChat layouts and social images

vscode-mermAId★ 187

Exploration into Copilot Chat-powered Diagram Generation

design-studio★ 180

An open source prototype sandbox for designers and product managers who build.

medical-illustration★ 178

面向 Codex、Claude Code 等 AI Agent 的医学绘图 Skill,基于可信证据制作医学插画、科普漫画与科研示意图,提供可编辑成果与审核记录。 · Evidence-backed medical illustration, comics and research figures for Codex, Claude Code and other AI agents, with editable output and review records.

mckinsey-style-visualization-skill★ 177

Agent Skill that turns messy notes into rendered strategy-consulting visuals, with SVG examples and validation.

open-motion★ 174

OpenMotion: The AI-Native Motion Design Platform, Redefining AI-Native Animation and Design. 🕹️

design-intelligence★ 162

RYUX gives AI agents the design intelligence to understand product context, make intentional design decisions, and evaluate what they create.

architecture-canvas★ 160

Chat with your documents to create and refine editable architecture diagrams. Local workspace, Excalidraw canvas, optional Tavily search.

design-md-figma★ 159

Figma plugin that extracts local style guidelines and generates DESIGN.md and SKILL.md files for AI tools such as Claude Code, Codex, Cursor, and other AI tools

shotluma★ 158

Open-source, local-first AI App Store screenshot editor.

ui★ 154

The shadcn for agent UI. A framework-agnostic design language for dense, AMOLED-black, multi-surface interfaces

More in Image, video & design