Nakkas

Declarative SVG generation where the AI designs the entire config and nakkas renders it. You get a single render_svg tool that accepts a JSON schema covering canvas, gradients, filters, animations (both CSS keyframes and SMIL), and a full element library including shapes, text, groups, and specialized layout groups like radial, grid, and scatter. The AI fills in every field from stroke styles to easing curves while you describe what you want in plain language. Preview returns a PNG, save writes to disk, and everything runs locally with zero external dependencies. Built for AI-native workflows: the schema uses rich describe() annotations so models know exactly what each field does. Good fit when you need programmatic vector graphics without touching Illustrator or writing SVG by hand.