Sayhi-bzb/CharDesk

A Unicode canvas for humans and AI. Draw diagrams, interfaces, and slides as editable text.

What it solves

CharDesk addresses the gap between human visual understanding and the way language models process information. While screenshots provide visual context, they are often noisy, consume significant visual tokens, and are difficult for AI to edit precisely. CharDesk solves this by using a Unicode grid as a shared visual language that remains a diagram to humans but stays as readable text for AI.

How it works

It provides an editable Unicode canvas where users can create diagrams, wireframes, and maps using text, symbols, box-drawing characters, and emojis. This creates a portable text representation of visual ideas that can be copied and pasted between a human and an AI. The workflow allows users to visually refine an idea, provide the compact text representation to an AI for analysis or revision, and then paste the AI's text output back into the canvas for further visual editing.

Who it’s for

It is designed for people who need to create flowcharts, architecture diagrams, system maps, and interface mockups that need to be shared with or edited by AI agents and language models.

Highlights

  • Three working modes: Offers Freeform drawing on an infinite grid, Structured building with editable boxes and arrows, and a Slides mode for text-based presentations.
  • AI-native format: The output is plain text or ANSI-styled text, making it directly compatible with LLM token sequences without needing a specialized AI provider.
  • Portable ecosystem: Includes a protocol for text interchange, a framework-independent viewer for web rendering, and compatible glyph assets.
  • Broad character support: Integrates Unicode symbols, CJK characters, emoji, and Nerd Font glyphs on a consistent grid.

Related

  • Project
    chatfire-AI/huobao-canvas

    A visual AI creation canvas that allows users to orchestrate text-to-image and video generation workflows using a node-based interface.

  • Project
    penecho/penecho

    PenEcho is an open‑source AI‑enhanced infinite canvas that lets you write, sketch, and attach documents, then ask LLMs to generate explanations, formulas, plots, or interactive widgets directly on the canvas. It supports multiple model back‑ends (Kimi, Claude, OpenAI, DeepSeek, etc.), offers a multi‑step “PenEcho Agent” for reading files and web research, and includes an optional cloud service for cross‑device sync and public sharing. The app runs locally (Node.js) with a secure six‑digit LAN guard, and the UI is available as a downloadable desktop binary or via npm.

  • Project
    hero8152/Infinite-Canvas

    A unified visual canvas that integrates multiple AI APIs for text, image, and video generation, including support for ComfyUI and various cloud model providers.

  • Project
    ddcat-ai/open-ai-canvas

    An open-source AI film and short-drama creation workbench that integrates an infinite canvas with multimodal generation tools to turn text briefs into cinematic assets.

  • Project
    tigerowo/infinite-canvas

    An open-source creative workbench that integrates an infinite canvas with AI image, video, and audio generation tools for iterative visual design.