* docs: add image search & generation design spec and implementation plan - Spec: dual-source image search (Openverse + Wikimedia), multi-provider image generation - Plan: 16 tasks covering types, server endpoints, settings UI, property panel, auto-search pipeline, MCP integration * feat(types): add image service types and imagePrompt to ImageNode * feat(server): add image service API key validation endpoint Adds POST /api/ai/image-service-test that validates credentials for openverse (client_credentials), openai/custom (Bearer + /v1/models), gemini (API key + v1beta/models), and replicate (Bearer + /v1/models). * feat(server): add multi-provider image generation endpoint * feat(server): add dual-source image search endpoint (Openverse + Wikimedia) POST /api/ai/image-search searches freely-licensed images via Openverse with automatic fallback to Wikimedia Commons on 429 rate-limit responses. Supports optional OAuth credentials for authenticated Openverse requests. * feat(store): add imageSearchStatuses to canvas store for runtime status tracking * feat(store): add image generation config and Openverse OAuth to agent settings * feat(editor): add Images tab to agent settings dialog Adds Popover primitive, ImagesPage component with Image Search (Openverse OAuth, test) and Image Generation (provider select, API key, model, base URL) sections, and wires them into the settings dialog sidebar. * feat(panels): add image search popover with Openverse/Wikimedia results grid * feat(panels): add image generate popover with multi-provider support * feat(panels): add Search and Generate buttons to image property section * feat(ai): update prompts to use imagePrompt instead of src for image nodes * feat(ai): add auto-search pipeline with Openverse/Wikimedia fallback * feat(ai): trigger auto image search after design generation completes * feat(mcp): implement G() operation for image search in batch design DSL Adds the G(parent, mode, prompt) operation to batch_design DSL that creates an image node and optionally fetches a real image URL via the image-search API when mode is "search". Converts executeLine to async to support the network call. * feat(mcp): auto-fill images after design refinement in layered pipeline * feat(ai): split imageSearchQuery and imagePrompt for search vs generation - ImageNode now has both imageSearchQuery (short keywords for search) and imagePrompt (long description for AI image generation) - AI prompts instruct LLM to generate both fields - Search pipeline and popovers use imageSearchQuery - Generate popover uses imagePrompt - Server-side simplifySearchQuery kept as fallback for manual input * fix(ai): hook auto image search into orchestrator completion path The primary generation path uses executeOrchestration -> insertStreamingNode, not applyNodesToCanvas/animateNodesToCanvas. Added scanAndFillImages call to orchestrator.ts after all sub-agents complete. Added debug logging. Removed plan/spec docs from git. * style(editor): remove provider names from image search ready status * fix(panels): clean up image gen error display and settings UI - Parse API error response to show concise message instead of raw JSON - Limit error text to 2 lines with line-clamp - Fix image gen test button sending wrong service name - Inline Image Search ready indicator with section header - Remove debug logging from image search pipeline * style(panels): allow up to 4 lines for image gen error message * fix: avoid 1-frame delay when resizing canvas (#60) rAF callbacks run before ResizeObserver in the same frame. Scheduling render in ResizeObserver via rAF defers it to the next frame. Invoke render() synchronously to leverage ResizeObserver's pre-paint timing and ensure immediate visual update. * feat(electron): implement desktop application structure and auto-updater - Introduced a new Electron desktop application with a structured directory for apps and packages. - Added auto-updater functionality to manage application updates seamlessly. - Created a comprehensive menu system for the desktop app. - Implemented logging capabilities for better debugging and error tracking. - Configured build settings for various platforms (macOS, Windows, Linux) using electron-builder. - Established TypeScript configurations for both the desktop and web applications. - Integrated Vite for the web application with support for React and Tailwind CSS. - Added icons and assets for the desktop application. * chore: update package versions to 0.5.0 across all package.json files and add pre-commit hook for version synchronization - Bumped version to 0.5.0 in package.json files for the main project, desktop app, web app, and all packages. - Introduced a pre-commit hook to automatically sync version numbers from branch names to all package.json files. * chore: update package versions to 0.5.0 and refactor Skia components - Bumped version to 0.5.0 in bun.lock and all relevant package.json files. - Refactored Skia components to utilize shared functionality from @zseven-w/pen-renderer, including image loading, hit testing, and path utilities. - Removed redundant code and improved modularity by re-exporting necessary functions and classes from the renderer package. * fix(panels): handle string fill values in icon nodes (#61) AI-generated icon/path nodes may have fill stored as a raw string instead of a PenFill[] array, causing "Cannot use 'in' operator" crash when selecting the node in the property panel. * chore: update documentation and project structure for monorepo organization - Added a new version bump command to synchronize all package.json files. - Updated the project structure to reflect a monorepo setup with organized workspaces for apps and packages. - Enhanced README files in multiple languages to include the new structure and commands. - Adjusted image paths in documentation to point to the correct locations for the desktop application. * feat(ai): incremental image search and improved image generation prompts - Refactor image search from batch post-generation to incremental queue: enqueueImageForSearch() triggers as each image node is inserted during streaming, so images appear progressively instead of all at once after generation completes. scanAndFillImages() remains as a final sweep. - Update imagePrompt guidance to avoid "transparent background" and similar phrases that many models cannot reliably produce. - Pass node width/height from image panel to generation endpoint for aspect-ratio-aware output (Gemini aspect ratio mapping, OpenAI size selection, Replicate dimensions). * feat(ai): multi-profile image generation config and cleaner error messages - Support multiple image generation profiles with active selection; first configured profile becomes default. Old single-config migrated automatically on hydrate. - Fix Gemini aspect ratio: move to generationConfig.imageConfig per API spec. - Extract clean error messages from provider JSON responses (Gemini error.message, OpenAI error.message, Replicate detail) instead of returning raw JSON text. - Remove destructive client-side regex that mangled error display. * feat(design-md): integrate design system panel and functionality - Added a new DesignMdPanel component for managing design system specifications. - Implemented functionality to toggle the design system panel in the editor layout and toolbar. - Introduced new commands for importing, exporting, and auto-generating design.md content. - Updated AI chat handlers to utilize design.md data for enhanced design generation. - Enhanced localization support for design system features across multiple languages. * perf(canvas): skip draw calls for nodes outside the viewport (#64) Add viewport culling in render() to avoid issuing CanvasKit draw calls for off-screen nodes. A 64px screen-space buffer is kept around the viewport edges so nearby nodes are pre-rendered, preventing pop-in during fast panning. * feat(utils): enhance Windows process spawning for CLI scripts - Updated the buildSpawnClaudeCodeProcess function to handle .cmd and .ps1 scripts appropriately. - Implemented PowerShell invocation for .ps1 files and ensured safe defaults for .cmd and .exe files. - Improved handling of command execution to avoid limitations of cmd.exe. * feat(ai): add support for Gemini CLI integration - Extended the AI provider options to include 'gemini' across various components and APIs. - Implemented functions for generating, validating, and connecting to the Gemini CLI. - Added Gemini-specific error handling and model fetching logic. - Updated UI components to display Gemini as a selectable provider with appropriate icons and labels. - Enhanced localization support for Gemini-related features in multiple languages. * feat(editor): warn before closing with unsaved changes Intercept window/tab close when isDirty is true: - Electron: native dialog with Save / Don't Save / Cancel - Web: beforeunload handler + confirm on New/Open actions - i18n: close-confirm strings for all 15 locales * feat(ipc): extract IPC handlers to a dedicated module - Moved IPC dialog handling and updater functions from main.ts to ipc-handlers.ts for better organization and maintainability. - Implemented file open/save dialogs, theme setting, and preferences management through IPC. - Enhanced updater functionality with state management and auto-update settings. - Improved code structure by separating concerns, making it easier to manage IPC-related logic. * feat(docs): update CLAUDE documentation and add new files for desktop and web apps - Enhanced CLAUDE.md with detailed module documentation references for `packages/` and `apps/`. - Updated `pen-core` description to include clone utilities in `pen-core`. - Added new documentation files for the desktop and web applications, outlining their structure, components, and functionalities. - Included IPC handler details in the desktop app documentation for better clarity on file dialogs and theme synchronization. * feat(docker): add Gemini CLI support and update documentation - Introduced a new Docker build stage for the Gemini CLI, allowing users to install and run it. - Updated the Dockerfile to include the installation of the Gemini CLI alongside existing CLI tools. - Enhanced README files in multiple languages to document the new `openpencil-gemini` image variant. - Added Gemini CLI connection instructions to the main README for better user guidance. * feat(docs): add Gemini CLI connection instructions to multiple language READMEs - Updated README files in German, Spanish, French, Hindi, Indonesian, Japanese, Korean, Portuguese, Russian, Thai, Turkish, Vietnamese, and both Traditional and Simplified Chinese to include connection instructions for the Gemini CLI. - Enhanced documentation to improve user guidance for connecting the Gemini CLI in agent settings. * perf(renderer): replace count-based text cache limits with memory-based eviction (#66) previous limits (PARA_CACHE_MAX=200, TEXT_CACHE_MAX=300) were too small for scenes with many nodes, causing constant cache churn and paragraph rebuilds every frame, which dropped FPS significantly during canvas pan. - switch to byte-budget limits (64 MB paragraphs, 256 MB bitmaps) - bitmap size measured exactly as cw*ch*4; paragraph WASM heap estimated as content.length*64+4096 - eviction uses Map insertion order (FIFO) instead of a separate string[] array, replacing O(n) array.shift() with O(1) Map.entries().next() - evict before insert so the budget check includes the incoming entry --------- Co-authored-by: Fini <fini.yang@gmail.com> Co-authored-by: leinaldo <60176594+leinaldo@users.noreply.github.com>
14 KiB
OpenPencil
A primeira ferramenta de design vetorial open-source nativa com IA do mundo.
Equipes de Agentes Concorrentes • Design-as-Code • Servidor MCP Integrado • Inteligência Multi-modelo
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
Clique na imagem para assistir ao vídeo de demonstração
Por que OpenPencil
🎨 Prompt → CanvasDescreva qualquer UI em linguagem natural. Veja-a aparecer no canvas infinito em tempo real com animação de streaming. Modifique designs existentes selecionando elementos e conversando. |
🤖 Equipes de Agentes ConcorrentesO orquestrador decompõe páginas complexas em sub-tarefas espaciais. Vários agentes de IA trabalham em diferentes seções simultaneamente — hero, features, footer — tudo em streaming paralelo. |
🧠 Inteligência Multi-ModeloAdapta-se automaticamente às capacidades de cada modelo. Claude recebe prompts completos com thinking; GPT-4o/Gemini desativam thinking; modelos menores (MiniMax, Qwen, Llama) recebem prompts simplificados para saída confiável. |
🔌 Servidor MCPInstalação com um clique no Claude Code, Codex, Gemini, OpenCode, Kiro ou Copilot CLIs. Faça design pelo seu terminal — leia, crie e modifique arquivos |
📦 Design-as-CodeArquivos |
🖥️ Roda em Qualquer LugarApp web + desktop nativo no macOS, Windows e Linux via Electron. Atualização automática a partir do GitHub Releases. Associação de arquivos |
Início Rápido
# Instalar dependências
bun install
# Iniciar servidor de desenvolvimento em http://localhost:3000
bun --bun run dev
Ou executar como aplicativo desktop:
bun run electron:dev
Docker
Várias variantes de imagem estão disponíveis — escolha a que se adequa às suas necessidades:
| Imagem | Tamanho | Inclui |
|---|---|---|
openpencil:latest |
~226 MB | Apenas aplicação web |
openpencil-claude:latest |
— | + Claude Code CLI |
openpencil-codex:latest |
— | + Codex CLI |
openpencil-opencode:latest |
— | + OpenCode CLI |
openpencil-copilot:latest |
— | + GitHub Copilot CLI |
openpencil-gemini:latest |
— | + Gemini CLI |
openpencil-full:latest |
~1 GB | Todas as ferramentas CLI |
Executar (apenas web):
docker run -d -p 3000:3000 ghcr.io/zseven-w/openpencil:latest
Executar com AI CLI (ex. Claude Code):
O chat de IA depende do login OAuth do Claude CLI. Use um volume Docker para persistir a sessão de login:
# Passo 1 — Login (apenas uma vez)
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
# Passo 2 — Iniciar
docker run -d -p 3000:3000 \
-v openpencil-claude-auth:/root/.claude \
ghcr.io/zseven-w/openpencil-claude:latest
Compilar localmente:
# Base (apenas web)
docker build --target base -t openpencil .
# Com um CLI específico
docker build --target with-claude -t openpencil-claude .
# Completo (todos os CLIs)
docker build --target full -t openpencil-full .
Design Nativo com IA
Do Prompt à UI
- Texto para design — descreva uma página e ela será gerada no canvas em tempo real com animação de streaming
- Orquestrador — decompõe páginas complexas em sub-tarefas espaciais para geração paralela
- Modificação de design — selecione elementos e descreva as alterações em linguagem natural
- Entrada de visão — anexe capturas de tela ou mockups para design baseado em referência
Suporte Multi-Agente
| Agente | Configuração |
|---|---|
| Claude Code | Sem configuração — usa o Claude Agent SDK com OAuth local |
| Codex CLI | Conectar nas Configurações do Agente (Cmd+,) |
| OpenCode | Conectar nas Configurações do Agente (Cmd+,) |
| GitHub Copilot | copilot login e depois conectar nas Configurações do Agente (Cmd+,) |
| Gemini CLI | Conectar nas Configurações do Agente (Cmd+,) |
Perfis de Capacidade de Modelo — adapta automaticamente prompts, modo de thinking e timeouts por nível de modelo. Modelos de nível completo (Claude) recebem prompts completos; nível padrão (GPT-4o, Gemini, DeepSeek) desativam thinking; nível básico (MiniMax, Qwen, Llama, Mistral) recebem prompts simplificados de JSON aninhado para máxima confiabilidade.
Servidor MCP
- Servidor MCP integrado — instalação com um clique no Claude Code / Codex / Gemini / OpenCode / Kiro / Copilot CLIs
- Detecção automática de Node.js — se não instalado, recurso automático para transporte HTTP e início automático do servidor MCP HTTP
- Automação de design pelo terminal: leia, crie e modifique arquivos
.opvia qualquer agente compatível com MCP - Fluxo de design em camadas —
design_skeleton→design_content→design_refinepara designs multi-seção de maior fidelidade - Recuperação segmentada de prompts — carregue apenas o conhecimento de design necessário (schema, layout, roles, icons, planning, etc.)
- Suporte a múltiplas páginas — crie, renomeie, reordene e duplique páginas via ferramentas MCP
Geração de Código
- React + Tailwind CSS, HTML + CSS, CSS Variables
- Vue, Svelte, Flutter, SwiftUI, Jetpack Compose, React Native
Funcionalidades
Canvas e Desenho
- Canvas infinito com pan, zoom, guias de alinhamento inteligentes e snapping
- Retângulo, Elipse, Linha, Polígono, Caneta (Bezier), Frame, Texto
- Operações booleanas — união, subtração, interseção com barra de ferramentas contextual
- Seletor de ícones (Iconify) e importação de imagens (PNG/JPEG/SVG/WebP/GIF)
- Auto-layout — vertical/horizontal com gap, padding, justify, align
- Documentos com múltiplas páginas e navegação por abas
Sistema de Design
- Variáveis de design — tokens de cor, número e string com referências
$variable - Suporte a múltiplos temas — vários eixos, cada um com variantes (Claro/Escuro, Compacto/Confortável)
- Sistema de componentes — componentes reutilizáveis com instâncias e substituições
- Sincronização CSS — propriedades personalizadas geradas automaticamente,
var(--name)na saída de código
Importação do Figma
- Importe arquivos
.figpreservando layout, preenchimentos, traços, efeitos, texto, imagens e vetores
Aplicativo Desktop
- macOS, Windows e Linux nativos via Electron
- Associação de arquivos
.op— clique duplo para abrir, bloqueio de instância única - Atualização automática a partir do GitHub Releases
- Menu de aplicativo nativo e diálogos de arquivo
Stack Tecnológica
| Frontend | React 19 · TanStack Start · Tailwind CSS v4 · shadcn/ui |
| Canvas | CanvasKit/Skia (WASM, acelerado por GPU) |
| Estado | Zustand v5 |
| Servidor | Nitro |
| Desktop | Electron 35 |
| IA | Anthropic SDK · Claude Agent SDK · OpenCode SDK · Copilot SDK |
| Runtime | Bun · Vite 7 |
| Formato de arquivo | .op — baseado em JSON, legível por humanos, compatível com Git |
Estrutura do Projeto
openpencil/
├── apps/
│ ├── web/ Aplicação web TanStack Start
│ │ ├── src/
│ │ │ ├── canvas/ Motor CanvasKit/Skia — desenho, sincronização, layout
│ │ │ ├── components/ UI React — editor, painéis, diálogos compartilhados, ícones
│ │ │ ├── services/ai/ Chat IA, orquestrador, geração de design, streaming
│ │ │ ├── stores/ Zustand — canvas, documento, páginas, histórico, IA
│ │ │ ├── mcp/ Ferramentas do servidor MCP para integração com CLI externo
│ │ │ ├── hooks/ Atalhos de teclado, soltar arquivos, colar do Figma
│ │ │ └── uikit/ Sistema de kit de componentes reutilizáveis
│ │ └── server/
│ │ ├── api/ai/ API Nitro — chat em streaming, geração, validação
│ │ └── utils/ Wrappers de cliente Claude CLI, OpenCode, Codex, Copilot
│ └── desktop/ Aplicativo desktop Electron
│ ├── main.ts Janela, fork do Nitro, menu nativo, atualizador automático
│ ├── ipc-handlers.ts Diálogos de arquivo nativos, sincronização de tema, preferências IPC
│ └── preload.ts Ponte IPC
├── packages/
│ ├── pen-types/ Definições de tipos para o modelo PenDocument
│ ├── pen-core/ Operações de árvore de documento, motor de layout, variáveis
│ ├── pen-codegen/ Geradores de código (React, HTML, Vue, Flutter, ...)
│ ├── pen-figma/ Parser e conversor de arquivos .fig do Figma
│ ├── pen-renderer/ Renderizador CanvasKit/Skia independente
│ └── pen-sdk/ SDK guarda-chuva (re-exporta todos os pacotes)
└── .githooks/ Sincronização de versão no pre-commit a partir do nome da branch
Atalhos de Teclado
| Tecla | Ação | Tecla | Ação | |
|---|---|---|---|---|
V |
Selecionar | Cmd+S |
Salvar | |
R |
Retângulo | Cmd+Z |
Desfazer | |
O |
Elipse | Cmd+Shift+Z |
Refazer | |
L |
Linha | Cmd+C/X/V/D |
Copiar/Recortar/Colar/Duplicar | |
T |
Texto | Cmd+G |
Agrupar | |
F |
Frame | Cmd+Shift+G |
Desagrupar | |
P |
Ferramenta caneta | Cmd+Shift+E |
Exportar | |
H |
Mão (pan) | Cmd+Shift+C |
Painel de código | |
Del |
Excluir | Cmd+Shift+V |
Painel de variáveis | |
[ / ] |
Reordenar | Cmd+J |
Chat IA | |
| Setas | Mover 1px | Cmd+, |
Configurações do agente | |
Cmd+Alt+U |
União booleana | Cmd+Alt+S |
Subtração booleana | |
Cmd+Alt+I |
Interseção booleana |
Scripts
bun --bun run dev # Servidor de desenvolvimento (porta 3000)
bun --bun run build # Build de produção
bun --bun run test # Executar testes (Vitest)
npx tsc --noEmit # Verificação de tipos
bun run bump <version> # Sincronizar versão em todos os package.json
bun run electron:dev # Desenvolvimento com Electron
bun run electron:build # Empacotamento do Electron
Contribuindo
Contribuições são bem-vindas! Consulte o CLAUDE.md para detalhes de arquitetura e estilo de código.
- Faça fork e clone
- Configure a sincronização de versão:
git config core.hooksPath .githooks - Crie uma branch:
git checkout -b feat/my-feature - Execute as verificações:
npx tsc --noEmit && bun --bun run test - Faça commit com Conventional Commits:
feat(canvas): add rotation snapping - Abra um PR contra
main
Roadmap
- Variáveis de design e tokens com sincronização CSS
- Sistema de componentes (instâncias e substituições)
- Geração de design com IA e orquestrador
- Integração com servidor MCP e fluxo de design em camadas
- Suporte a múltiplas páginas
- Importação do Figma
.fig - Operações booleanas (união, subtração, interseção)
- Perfis de capacidade multi-modelo
- Reestruturação em monorepo com pacotes reutilizáveis
- Edição colaborativa
- Sistema de plugins
Contribuidores
Comunidade
Star History
Licença
MIT — Copyright (c) 2026 ZSeven-W