openpencil

Note: There is another open-source project with the same name — OpenPencil, focused on Figma-compatible visual design with real-time collaboration. This project focuses on AI-native design-to-code workflows.

Why OpenPencil

🎨 Prompt → Canvas

Describe any UI in natural language. Watch it appear on the infinite canvas in real-time with streaming animation. Modify existing designs by selecting elements and chatting.

🤖 Concurrent Agent Teams

The orchestrator decomposes complex pages into spatial sub-tasks. Multiple AI agents work on different sections simultaneously — hero, features, footer — all streaming in parallel with per-member canvas indicators.

🧠 Multi-Model Intelligence

Automatically adapts to each model's capabilities. Claude gets full prompts with thinking; GPT-4o/Gemini disable thinking; smaller models (MiniMax, Qwen, Llama) get simplified prompts for reliable output.

🔌 MCP Server

One-click install into Claude Code, Codex, Gemini, OpenCode, Kiro, or Copilot CLIs. Design from your terminal — read, create, and modify .op files through any MCP-compatible agent.

🎨 Style Guides

Built-in style guide library with tag-based fuzzy matching. Apply visual styles (glassmorphism, brutalist, retro, etc.) to AI-generated designs. MCP tools for external agent access.

📦 Design-as-Code

.op files are JSON — human-readable, Git-friendly, diffable. Design variables generate CSS custom properties. Code export to React + Tailwind or HTML + CSS.

🖥️ Runs Everywhere

Web app + native desktop on macOS, Windows, and Linux — one Rust core, a single self-contained binary, no browser engine. .op file association — double-click to open.

⌨️ CLI — op

Control the design tool from your terminal. op design, op insert — batch design DSL, node manipulation. Pipe in from files or stdin. Works with desktop app or web server.

🎯 Multi-Platform Code Export

Export to React + Tailwind, HTML + CSS, Vue, Svelte, Flutter, SwiftUI, Jetpack Compose, React Native — all from one .op file. Design variables become CSS custom properties.

🧩 Embeddable SDK

op-web-sdk (vanilla) + op-web-sdk-react / op-web-sdk-vue adapters — embed a read-only .op viewer in your own app, powered by the same wasm renderer the editor ships.

🛡️ Design System Kit

Manage reusable UIKits with style switching and component composition. Import/export kits from .pen files. Built-in registry with MCP tools for external access.

Install

macOS (Homebrew):

brew tap zseven-w/openpencil
brew install --cask openpencil

Windows (Scoop):

scoop bucket add openpencil https://github.com/zseven-w/scoop-openpencil
scoop install openpencil

Linux / Windows direct download: GitHub Releases — .exe (Windows), .AppImage / .deb (Linux)

CLI (op):

brew install zseven-w/openpencil/op

Or use the install script (macOS / Linux):

curl -fsSL https://raw.githubusercontent.com/ZSeven-W/openpencil/main/scripts/install-op.sh | bash

To allow the newest pre-release:

curl -fsSL https://raw.githubusercontent.com/ZSeven-W/openpencil/main/scripts/install-op.sh | OP_PRERELEASE=1 bash

Windows PowerShell:

irm https://raw.githubusercontent.com/ZSeven-W/openpencil/main/scripts/install-op.ps1 | iex

To allow the newest pre-release:

$env:OP_PRERELEASE = "1"; irm https://raw.githubusercontent.com/ZSeven-W/openpencil/main/scripts/install-op.ps1 | iex

Cloning (with submodules)

git clone --recurse-submodules https://github.com/ZSeven-W/openpencil.git
# Or already cloned — sync first so stale submodule URLs pick up .gitmodules changes:
git submodule sync --recursive && git submodule update --init --recursive

Three submodules live under vendor/, all public and fetched over HTTPS (no SSH key needed): jian (GPU-Skia UI framework — widgets/render/events), casement (winit fork), and agent (agent-rs — cross-product Rust agent runtime, shared by OP + Zode). vendor/anthropic-agent-sdk is tracked in-tree, not a submodule.

Quick Start (Development)

# Web dev server (builds the CanvasKit wasm bundle, then runs the headless web host)
bash scripts/start-web-rust.sh

Or run as a desktop app:

cargo run -p op-host-desktop

Prerequisites: Rust (stable) to build the product. Bun >= 1.0 and Node.js >= 18 are only needed for the web SDK under packages/.

Docker

Tagged Rust releases publish a single web-host image. The retired TypeScript images with bundled AI CLIs are no longer published.

The web UI exposes built-in agent profiles only; Claude/Codex/OpenCode/Copilot/Gemini CLI tooling is not bundled into Docker images.

Run:

docker run -d -p 3100:3100 ghcr.io/zseven-w/openpencil-web:v0.8.0

Then open http://localhost:3100/.

Build locally:

docker build -f Dockerfile.web-rust -t openpencil-web-rust .
docker run -p 3100:3100 openpencil-web-rust

AI-Native Design

Prompt to UI

• Text-to-design — describe a page, get it generated on canvas in real-time with SSE streaming animation
• Orchestrator — decomposes complex pages into spatial sub-tasks for parallel generation
• Agent Teams — concurrent team members with delegate tool, per-member canvas indicators, and fallback strategies
• Design modification — select elements, then describe changes in natural language
• Vision input — attach screenshots or mockups for reference-based design
• Style Guides — apply visual styles (glassmorphism, brutalist, retro, etc.) via tag-based fuzzy matching
• Anti-slop — cross-generation diversity tracking to avoid repetitive AI output

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.

i18n — Full interface localization in 15 languages: English, 简体中文, 繁體中文, 日本語, 한국어, Français, Español, Deutsch, Port