Enables AI assistants to analyze code repositories and generate self-contained interactive HTML5/SVG architecture diagrams from project structure or existing Mermaid diagrams, fully air-gapped with no external dependencies.
Enables AI coding assistants to generate and iteratively revise auto-laid-out, hand-drawn diagrams across 25 types — architecture, flowcharts, sequence, ER, Gantt, and charts — from natural-language descriptions, with SVG/PNG export. It can also persist a system as a version-controlled, queryable architecture knowledge graph, running fully offline in Cursor, Claude Code, and Windsurf without API keys.
Enables AI assistants in Cursor, Claude Code, and Windsurf to turn plain descriptions of components, actors, or data into auto-laid-out, editable hand-drawn diagrams across 25 types — including architecture, flowcharts, sequence diagrams, Gantt charts, and charts — with architecture-aware styling and natural-language revision. It can optionally persist a system as a version-controlled, queryable knowledge graph, and it runs fully offline with no API keys, exporting to SVG and PNG.
Enables AI coding assistants to turn natural-language descriptions of systems and data into editable, auto-laid-out Excalidraw diagrams across 25 types — from architecture and sequence diagrams to Gantt charts and scatter plots — plus optionally persist the architecture as a queryable, version-controlled knowledge graph. Runs fully offline with export to SVG and PNG, and diagrams can be revised afterward in natural language.
Enables AI coding assistants to turn system architecture into auto-laid-out, editable Excalidraw diagrams across 25 diagram types — architecture, sequence, flowcharts, state machines, ER models, swimlanes, Gantt, and charts — with architecture-aware styling, SVG/PNG export, and natural-language revision. It can also persist the system as a version-controlled, queryable knowledge graph, running fully offline without API keys.
Enables AI coding agents to pull focused, token-bounded context from a local structural code graph stored in SQLite, so they can locate relevant code, traverse relationships between entities, and carry recorded mistakes into later sessions instead of reading whole files. It also supports serving that context over an authenticated local HTTP dashboard.
