Generate 25+ types of hand-drawn Excalidraw diagrams - flowcharts, sequence, architecture, mind maps, ER, UML, kanban, bar/line/radar charts - from structured input with Sugiyama auto-layout and CJK support. Reads and modifies .excalidraw files, exports SVG. Python, local, no API keys required.
An MCP server that generates beautiful Excalidraw architecture diagrams with perfect auto-layout, stateful editing, and architecture-aware component styling.
Enables AI agents to create, modify, and share diagrams on a live Excalidraw canvas through MCP tools, supporting shapes, text, arrows, batch operations, and export to shareable links with images.
Standalone backend for a self-hosted Excalidraw fork with per-board access control, providing an MCP remote endpoint that lets AI agents draw on real collaboration boards as specific users.
Generates hand-drawn Excalidraw diagrams from natural language prompts or structured descriptions, with tools for creating, listing, and opening diagrams directly in the browser.
Enables AI agents to programmatically control a live Excalidraw canvas with element-level CRUD operations and real-time synchronization. It supports iterative diagramming through scene descriptions, screenshots, and advanced layout tools for collaborative AI-human workflows.
The diagram-quality layer for AI agents — an opinionated Excalidraw methodology (isomorphism test, evidence artifacts, multi-zoom, container discipline) plus a render-view-fix loop. Accepts skeleton and Mermaid input, 5 publishable themes, dual Node/Python renderer.
Proven on a 77-diagram published book.
Streams hand-drawn Excalidraw diagrams with smooth viewport camera control and interactive fullscreen editing, enabling diagram creation via natural language.
MCP server enabling AI assistants to read and write Obsidian notes, create and edit Excalidraw drawings, and run Excalidraw scripts via natural language commands.