Our take
Activeregular commits and releases- Activity
- 83
- Community
- 43
- Issues
- 66
- Pull requests
- 82
+826 stars in the last 30 days
- Merges more pull requests than 92% of the projects we track
- Releases more often than 82% of the projects we track
OpenPencil is a capable, actively maintained option for programmable design work, but its rapid development and concentrated contributor base make it worth validating against your files and team workflow before adopting broadly.
Good fit if
- You work with Figma files and want CLI, MCP, or AI-assisted ways to inspect and change them.
- You want a desktop or browser-based editor with peer-to-peer collaboration and no required account.
- Your team can use a TypeScript-based tool and is comfortable with an MIT-licensed project that is actively evolving.
Look elsewhere if
- You need a fully mature, proven replacement with no known compatibility gaps; the project says it still has rough edges and points to a roadmap of Figma compatibility gaps.
- Your team cannot accept reliance on a project where most contributions come from one person, despite recent activity from a wider contributor group.
- You need every AI provider and model to work consistently in the browser; the project documents provider and model compatibility limitations.
All health signals
| Last commit | 2026-10-06 (today) |
|---|---|
| Commits, last 90 days | 100+ |
| Releases, last 12 months | 35 (latest v0.15.1, 2026-09-18) |
| Contributors | 38 (top contributor: 90% of commits) |
| Issues closed, last 90 days | 10+ (typically closed in 2 days) |
| Project age | 7 months |
Checked on 2026-10-06 with the GitHub API.
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
9,852Forks
1,068Change since Nov 14, 2026: +16 stars·+4 forks
Overview
OpenPencil is an open-source design editor for working with .fig and .pen files. It aims to make design work more programmable than a conventional visual editor: users can edit in the canvas, automate documents with a CLI or MCP tools, and connect AI providers using their own API keys.
It runs as a desktop app or web app, and also offers a headless Vue SDK for building custom editing surfaces. The project is in active development; its README describes it as usable today, with some rough edges and compatibility gaps to check against your workflows.
Key Features
- Open and write native Figma files, and work with supported Pencil documents.
- Use an AI chat assistant with more than 100 tools to create and modify design nodes, using a compatible provider and your own API key.
- Inspect, query, lint, convert, export, and script documents through the CLI, including XPath queries and Figma Plugin API access.
- Connect AI agents through an MCP server to inspect, modify, and export design documents.
- Build reusable components and variants, and preview interactive controls such as switches, sliders, and tabs on the canvas.
- Collaborate peer-to-peer over WebRTC, with shared edits, cursors, presence, and follow mode.
- Export designs to formats including SVG, PDF, HTML, JSX, and Storybook stories, or import HTML/CSS as editable layers.
- Embed headless Vue components and composables through the SDK to create custom editors.
Use Cases
- Designers who need to open or modify
.figfiles without relying exclusively on Figma’s editor. - Design-system teams that want to audit colors, typography, spacing, naming, and accessibility across documents.
- Developers and coding-agent users who want to automate design edits or export design elements into code workflows.
- Teams that want to co-edit directly without setting up a collaboration server or account.
- Product teams building workflow-specific editors with the Vue SDK rather than starting from a canvas implementation.
What you need
Detected in the repository
- Node.js (from package.json)
- A test suite and automated checks on GitHub Actions
License in plain words
MITpermissive
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the copyright and license notice
- Share your changes: no
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
For the CLI, install with:
npm install -g @open-pencil/cli
You can also try the web app or install the desktop app from the releases page. See the README and documentation for setup and usage details.
Considerations
- The project is active, with regular commits and releases, and issues are being closed promptly. However, contribution is highly concentrated in one person, which is a continuity risk for teams depending on sustained maintenance.
- OpenPencil is still evolving. Validate file compatibility and essential editing workflows with representative documents before making it a team-wide standard.
- The AI assistant requires users to provide an API key. Provider and model behavior varies, and not every provider works in the browser.
- The CLI requires Node.js. Desktop builds require platform-specific Tauri prerequisites, including Rust; the web app has browser-version requirements. The project does not list Docker as a setup route.
- The MIT license permits broad use, but teams should still review its terms for their distribution and attribution needs.
Found this useful?
Share it with someone who would like open-pencil.