open-pencil/open-pencil

AI-native design editor. Open-source Figma alternative.

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 9 minutes ago
Added to GitGenius on September 1st, 2026
Created on February 27th, 2026
Open Issues & Pull Requests: 46 (+0)
GitHub issues: Enabled
Number of forks: 793
Total Stargazers: 8,203 (+2)
Total Subscribers: 54 (+0)

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Issue API getrepoissuespagesummary failed: 429 Rate limit exceeded. Please try again later.

Detailed Description

OpenPencil is an open-source design editor that provides a Figma alternative with built-in AI capabilities and programmable toolkit features.

The tool addresses the need for an open alternative to proprietary design software while adding AI-native workflows. It reads and writes native Figma `.fig` files alongside its own `.pen` format, allowing designers to work with existing Figma documents. The AI component lets users describe designs in natural language, with over ninety tools available to create and modify nodes across multiple LLM providers including OpenRouter, Anthropic, OpenAI, Google AI, and others. Beyond editing, the project ships as a programmable toolkit: a headless Vue SDK enables embedding the editor into other applications, XPath queries allow document inspection without opening the UI, and a CLI supports linting, token extraction, format conversion, and design-to-code export as JSX or Tailwind CSS.

Adoption suits teams seeking an open-source design tool with extensibility as a first-class concern. The desktop application runs on macOS, Windows, and Linux via Tauri at approximately seven megabytes, while a web version operates as a PWA without installation. Real-time collaboration works peer-to-peer over WebRTC without requiring accounts or servers. The project includes auto layout and CSS Grid support via Yoga WASM, component and variant management, image vectorization through Recraft or fal.ai, and design token analysis. Those building custom editing surfaces or integrating design workflows into larger systems will find the Vue SDK and MCP server support particularly relevant. The tool explicitly targets AI agents through Claude Code, Codex, and Gemini CLI integrations.

Development remains actively ongoing with acknowledged rough edges as features evolve. The project maintains public documentation, a roadmap, and an llms.txt file for AI context. A web demo is available for immediate evaluation without installation or download.