claude-skill

penecho: AI Canvas

Name: penecho: AI Canvas
Author: penecho

Unlock visual thinking with penecho, a shared canvas for founders and educators, backed by 1.7k+ GitHub stars.

1,717 stars192 forksJavaScriptHealth Score 9/10Updated 7/27/2026100% free · open source

What it does

Penecho allows users to collaborate with AI on a shared canvas, enabling handwriting, equations, diagrams, and spatial reasoning beyond traditional chat box interactions.

Install / run

Clone the repository from https://github.com/penecho/penecho and follow the setup instructions in the README

When to use it

•When creating complex diagrams or equations that require spatial reasoning and collaboration
•When needing to annotate or mark up images or documents with handwritten notes
•When developing educational content that requires interactive, visual explanations

Quick start

1Navigate to the cloned repository and run the development server using the command specified in the README
2Open a web browser and access the Penecho application at the URL indicated in the README
3Create a new canvas and explore the drawing and annotation tools
4Invite collaborators to join the canvas and experiment with real-time collaboration features
5Experiment with AI-powered features, such as equation recognition and spatial reasoning, as described in the README

Ready-to-paste prompt

Open the Penecho canvas and draw a simple equation, such as '2x + 5 = 11', to demonstrate the AI-powered equation recognition and solution capabilities

Heads up: Ensure that your development environment meets the prerequisites specified in the README, including the required version of Node.js and any necessary dependencies, to avoid compatibility issues

Saves to your device

Topics

canvas

claude

codex

education

handwriting

nodejs

visual-thinking

How penecho: AI Canvas works

Codeflow

Free to inspect

Penecho: AI Canvas is a large JavaScript project (~37k lines across 56 code files, plus 39 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, AGPL-3.0 license, has a test suite.

Size

Large codebase

~37k lines · 56 code files · ~5 h to skim

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Node.js

No API keys detected

JavaScript 90%CSS 7%HTML 3%

Where to start reading