#4242nd of 80 in Agent platformsFor image, video and design, image and design
openpencil
Vector design editor that generates UI on canvas from prompts
- Stars
- 7.2k
- License
- MIT
- Last commit
- Nov 2026
- Language
- Rust
2,285 on 21 Apr 20267,209 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
OpenPencil is a Rust vector design editor that runs as a native desktop app or a headless web host. It generates and edits UI layouts from prompts, splitting pages across parallel agents, and saves designs as JSON `.op` files. It exports to React + Tailwind, HTML + CSS, Vue, Svelte, Flutter, SwiftUI and more, and ships an MCP server and an `op` CLI so external coding agents can edit designs.
Who it is for: Designers and developers who want AI-generated UI designs as code
Strengths
- `.op` files are plain JSON, so designs diff and version cleanly in Git
- Built-in MCP server over stdio or local HTTP, no Node.js required
- Code export to React, Vue, Svelte, Flutter, SwiftUI, Compose and React Native
- Works with 9+ API providers plus Claude Code, Codex, OpenCode and Copilot CLIs
Weaknesses
- Web host and Docker image support only built-in API-key agents, not CLI agents
- Building from source needs three git submodules (jian, casement, agent)
- No tagged release on the repository; Docker images are versioned separately
- Output quality varies by model; smaller models get simplified prompts
What it needs
- Docker + Compose
- Needs Rust toolchain (build from source), LLM provider API key or agent CLI, Bun and Node.js (web SDK only)
- Models: Anthropic, OpenAI, Google Gemini, DeepSeek, Kimi
- port 3100
Quick answers
Is openpencil open source?
Yes. Its code is on GitHub under the MIT license.
Can you run openpencil with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Agent platforms
See all 80| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |