Coding agents on cloud machines with a record of every session
Specialised AI modules that connect to your stack, run on their own and report where you work
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
IT
Pricing model
Free trial
Contact for pricing
Pricing
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.
Not given
Key features
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
Magic Red Team - AI agents identify security risks and suggest fixes
Magic Growth - Analyzes analytics and proposes experiments
Magic Bug Finder - Detects bugs before users encounter them
Magic Visual Testing - Catches visual regressions across screens and devices
Reports in Slack, Teams or email
Integrates with GitHub, Linear, Analytics and staging environments
Magic Studio - Custom AI builds for enterprise
Each module works independently
What makes it different
Your Agent. Not a Vendor's.
The work ends. The proof remains.
Complete session records and operational transparency
Use any model with visible per-token pricing
Modular design - activate only the AI modules you need
Specialized AI agents - each module does one job extremely well