OpenPencil is an open-source, AI-native vector design tool positioned as a modern alternative to Pencil. Created in 2026, it has already gathered about 6,300 stars on GitHub and is under very active development.
OpenPencil is built around prompt-to-canvas design: describe a UI in natural language and watch it appear on a live, infinite canvas, then refine it by selecting elements and chatting. Its signature feature is concurrent Agent Teams — an orchestrator decomposes a complex page into spatial sub-tasks and multiple AI agents design different sections simultaneously, with per-member progress shown on the canvas. A multi-model layer adapts prompting to whatever model you connect, from Claude and GPT-4o to smaller open models, and a built-in MCP server lets external coding agents design through .op files. Those files are plain JSON — human-readable, diffable, and Git-friendly — and designs export to React + Tailwind, HTML + CSS, Vue, Svelte, Flutter, SwiftUI, Jetpack Compose, and React Native. The app runs on the web and as native desktop builds for macOS, Windows, and Linux from a single Rust core.
OpenPencil is free and open source under the MIT license. You bring your own model API keys for the AI features.
Designers and developers who want AI-generated UI they can actually own, version, and export to production code — without a proprietary file format in the way.