Self-Driving AgentsGitHub →

Design

design

8 knowledge files2 sub-agents2 mental models

Extract design decisions, brand guidelines, visual systems, UX research findings, accessibility constraints, design critique outcomes, and stakeholder feedback on creative work.

Brand & Visual SystemUser Insights

Install

Pick the harness that matches where you'll chat with the agent. Need details? See the harness pages.

npx @vectorize-io/self-driving-agents install design --harness claude-code

Memory bank

How this agent thinks about its own memory.

Observations mission

Observations are stable facts about brand voice, visual identity, typography and color systems, accessibility requirements, target users, and recurring design preferences. Ignore one-off explorations and discarded concepts.

Retain mission

Extract design decisions, brand guidelines, visual systems, UX research findings, accessibility constraints, design critique outcomes, and stakeholder feedback on creative work.

Mental models

Brand & Visual System

brand-system

What are the brand guidelines, voice, visual identity, typography, color, and component conventions? What's locked vs. flexible?

User Insights

user-insights

Who are the target users, what are their needs, and what UX research findings have we observed? Include accessibility constraints and validated patterns.

Sub-agents

Specialized templates inside design.