Lets an AI describe diagram structure in natural language and produces auto-laid-out, editable hand-drawn Excalidraw files across 25 diagram types, from architecture and sequence diagrams to ER models, swimlanes, Gantt charts, and scatter plots. Runs fully offline inside Cursor, Claude Code, and Windsurf with no API keys, and can revise diagrams or persist an architecture knowledge graph for querying and linting.
Enables AI assistants to turn plain-language descriptions of systems, flows, and data into 25 kinds of fully laid-out, hand-drawn Excalidraw diagrams — architecture, sequence, ER, swimlane, Gantt, charts and more — with auto-styling for 50+ technologies and revision in natural language. Runs fully offline, exports to SVG and PNG without a browser or Node.js, and can optionally persist the architecture as a queryable knowledge graph.
Enables AI coding assistants to turn natural-language architecture and data descriptions into editable, auto-laid-out hand-drawn diagrams across 25 types, with natural-language revisions, SVG/PNG export, and an optional queryable architecture knowledge graph, fully offline without API keys.
Enables AI assistants to turn natural-language descriptions of systems, flows, and data into hand-drawn-style Excalidraw diagrams across 25 types—architecture, sequence, swimlane, ER, Gantt, charts and more—with automatic layout, architecture-aware styling of 50+ technologies, and export to SVG/PNG. It also lets users revise diagrams conversationally and optionally persist their system as a queryable, version-controlled architecture knowledge graph, all running fully offline with no API keys.
Enables AI agents to drive a live SVG/vector editor, allowing a full observe-and-act loop on a canvas with real tools, state reading, and PNG rendering.