GitHub - ZSeven-W/openpencil: 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.

The world's first open-source AI-native vector design tool.
_{Concurrent Agent Teams • Design-as-Code • Built-in MCP Server • Multi-model Intelligence}

English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Français · Español · Deutsch · Português · Русский · हिन्दी · Türkçe · ไทย · Tiếng Việt · Bahasa Indonesia

_{Click the image to watch the demo video}

Why OpenPencil

Quick Start

# Install dependencies
bun install

# Start dev server at http://localhost:3000
bun --bun run dev

Or run as a desktop app:

Prerequisites: Bun >= 1.0 and Node.js >= 18

Docker

Multiple image variants are available — pick the one that fits your needs:

Run (web only):

docker run -d -p 3000:3000 ghcr.io/zseven-w/openpencil:latest

Run with AI CLI (e.g. Claude Code):

The AI chat relies on Claude CLI OAuth login. Use a Docker volume to persist the login session:

# Step 1 — Login (one-time)
docker volume create openpencil-claude-auth
docker run -it --rm \
  -v openpencil-claude-auth:/root/.claude \
  ghcr.io/zseven-w/openpencil-claude:latest claude login

# Step 2 — Start
docker run -d -p 3000:3000 \
  -v openpencil-claude-auth:/root/.claude \
  ghcr.io/zseven-w/openpencil-claude:latest

Build locally:

# Base (web only)
docker build --target base -t openpencil .

# With a specific CLI
docker build --target with-claude -t openpencil-claude .

# Full (all CLIs)
docker build --target full -t openpencil-full .

AI-Native Design

Prompt to UI

• Text-to-design — describe a page, get it generated on canvas in real-time with streaming animation
• Orchestrator — decomposes complex pages into spatial sub-tasks for parallel generation
• Design modification — select elements, then describe changes in natural language
• Vision input — attach screenshots or mockups for reference-based design

Multi-Agent Support

Model Capability Profiles — automatically adapts prompts, thinking mode, and timeouts per model tier. Full-tier models (Claude) get complete prompts; standard-tier (GPT-4o, Gemini, DeepSeek) disable thinking; basic-tier (MiniMax, Qwen, Llama, Mistral) get simplified nested-JSON prompts for maximum reliability.

MCP Server

• Built-in MCP server — one-click install into Claude Code / Codex / Gemini / OpenCode / Kiro / Copilot CLIs
• Auto-detects Node.js — if not installed, falls back to HTTP transport and auto-starts the MCP HTTP server
• Design automation from terminal: read, create, and modify .op files via any MCP-compatible agent
• Layered design workflow — design_skeleton → design_content → design_refine for higher-fidelity multi-section designs
• Segmented prompt retrieval — load only the design knowledge you need (schema, layout, roles, icons, planning, etc.)
• Multi-page support — create, rename, reorder, and duplicate pages via MCP tools

Code Generation

• React + Tailwind CSS, HTML + CSS, CSS Variables
• Vue, Svelte, Flutter, SwiftUI, Jetpack Compose, React Native

CLI — op

Install globally and control the design tool from your terminal:

npm install -g @zseven-w/openpencil

op start                     # Launch desktop app
op design @landing.txt       # Batch design from file
op insert '{"type":"RECT"}'  # Insert a node
op export react --out .      # Export to React + Tailwind
op import:figma design.fig   # Import Figma file
cat design.dsl | op design - # Pipe from stdin

Supports three input methods: inline string, @filepath (read from file), or - (read from stdin). Works with desktop app or web dev server. See CLI README for full command reference.

Features

Canvas & Drawing

• Infinite canvas with pan, zoom, smart alignment guides, and snapping
• Rectangle, Ellipse, Line, Polygon, Pen (Bezier), Frame, Text
• Boolean operations — union, subtract, intersect with contextual toolbar
• Icon picker (Iconify) and image import (PNG/JPEG/SVG/WebP/GIF)
• Auto-layout — vertical/horizontal with gap, padding, justify, align
• Multi-page documents with tab navigation

Design System

• Design variables — color, number, string tokens with $variable references
• Multi-theme support — multiple axes, each with variants (Light/Dark, Compact/Comfortable)
• Component system — reusable components with instances and overrides
• CSS sync — auto-generated custom properties, var(--name) in code output

Figma Import

• Import .fig files with layout, fills, strokes, effects, text, images, and vectors preserved

Desktop App

• Native macOS, Windows, and Linux via Electron
• .op file association — double-click to open, single-instance lock
• Auto-update from GitHub Releases
• Native application menu and file dialogs

Tech Stack

Project Structure

openpencil/
├── apps/
│   ├── web/                 TanStack Start web app
│   │   ├── src/
│   │   │   ├── canvas/      CanvasKit/Skia engine — drawing, sync, layout
│   │   │   ├── components/  React UI — editor, panels, shared dialogs, icons
│   │   │   ├── services/ai/ AI chat, orchestrator, design generation, streaming
│   │   │   ├── stores/      Zustand — canvas, document, pages, history, AI
│   │   │   ├── mcp/         MCP server tools for external CLI integration
│   │   │   ├── hooks/       Keyboard shortcuts, file drop, Figma paste
│   │   │   └── uikit/       Reusable component kit system
│   │   └── server/
│   │       ├── api/ai/      Nitro API — streaming chat, generation, validation
│   │       └── utils/       Claude CLI, OpenCode, Codex, Copilot wrappers
│   ├── desktop/             Electron desktop app
│   │   ├── main.ts          Window, Nitro fork, native menu, auto-updater
│   │   ├── ipc-handlers.ts  Native file dialogs, theme sync, prefs IPC
│   │   └── preload.ts       IPC bridge
│   └── cli/                 CLI tool — `op` command
│       ├── src/commands/    Design, document, export, import, node, page, variable commands
│       ├── connection.ts    WebSocket connection to running app
│       └── launcher.ts      Auto-detect and launch desktop app or web server
├── packages/
│   ├── pen-types/           Type definitions for PenDocument model
│   ├── pen-core/            Document tree ops, layout engine, variables
│   ├── pen-codegen/         Code generators (React, HTML, Vue, Flutter, ...)
│   ├── pen-figma/           Figma .fig file parser and converter
│   ├── pen-renderer/        Standalone CanvasKit/Skia renderer
│   └── pen-sdk/             Umbrella SDK (re-exports all packages)
└── .githooks/               Pre-commit version sync from branch name

Keyboard Shortcuts

Scripts

bun --bun run dev          # Dev server (port 3000)
bun --bun run build        # Production build
bun --bun run test         # Run tests (Vitest)
npx tsc --noEmit           # Type check
bun run bump <version>     # Sync version across all package.json
bun run electron:dev       # Electron dev
bun run electron:build     # Electron package
bun run cli:dev            # Run CLI from source
bun run cli:compile        # Compile CLI to dist

Contributing

Contributions are welcome! See CLAUDE.md for architecture details and code style.

1. Fork and clone
2. Set up version sync: git config core.hooksPath .githooks
3. Create a branch: git checkout -b feat/my-feature
4. Run checks: npx tsc --noEmit && bun --bun run test
5. Commit with Conventional Commits: feat(canvas): add rotation snapping
6. Open a PR against main

Roadmap

• Design variables & tokens with CSS sync
• Component system (instances & overrides)
• AI design generation with orchestrator
• MCP server integration with layered design workflow
• Multi-page support
• Figma .fig import
• Boolean operations (union, subtract, intersect)
• Multi-model capability profiles
• Monorepo restructure with reusable packages
• CLI tool (op) for terminal control
• Collaborative editing
• Plugin system

Contributors

Community

Join our Discord

Star History

License

MIT — Copyright (c) 2026 ZSeven-W