Coding agents on cloud machines with a record of every session
Stage
Startup
Not given
Founded
2026
Not given
Based in
Not given
Not given
Pricing model
Paid
Free trial
Pricing
Not given
Free trial: two machines, up to 2 vCPU and 4 GiB. Cuna Inference pricing: models available at varying rates, such as GLM-5.2 at $1.00 per million input tokens and $4.00 per million output tokens.
Key features
2,746 design styles spanning design movements, brands, and cultural traditions
DESIGN.md machine-readable specifications for each style
MCP integration for direct AI access
Shareable links that work for 15 minutes
Worked examples across real scenarios
Free browsing and previews of all styles
Filters by use, mood, color and era
New styles added every week
Downloadable DESIGN.md files
13 spec sections per style including colors, typography, spacing, motion, and techniques
Isolated session execution with bounded authority
Web console for machine management
Complete action recording and visibility
OpenAI-compatible Chat Completions API
OpenCuna terminal agent
Multiple model provider support
Cuna Memory for agent state persistence
Token-based pay-as-you-go pricing
What makes it different
Enables non-designers to produce designer-quality results by having AI apply the design style
Packages established design styles from art history, cultural traditions, and major brands as AI-readable specs
One-time credit purchase model with no subscription and non-expiring credits
Direct integration with popular AI assistants including Claude, ChatGPT, and Cursor
Unlimited reuse after single one-time credit purchase
Your Agent. Not a Vendor's.
The work ends. The proof remains.
Complete session records and operational transparency