On-demand cloud macOS for AI agents, billed per minute
Edge-first agent serving framework for cloud, OpenWrt, and device deployment
Stage
Startup
Not given
Founded
2026
Not given
Based in
Not given
Not given
Pricing model
Paid
Not given
Pricing
$0.90 per hour, billed per minute. Prepaid credit starts at $10, never expires and needs no subscription. Bigger top-ups add up to 20% bonus credit: $100 buys 133 hours. 7-day money-back guarantee on first purchase.
Not given
Key features
Real macOS on Apple M6 or M5 Pro silicon, ready in about a minute
Full admin access with no password prompts
Xcode 27 preinstalled with Homebrew, Node, Python and CocoaPods
iOS Simulator with screenshots and screen recordings
Persistent 20 GB encrypted drive between sessions
Control via MCP, CLI, API or SSH
App Store submissions and TestFlight uploads
Secrets management without chat exposure
Desktop view and control in browser
Deploy agents across cloud, OpenWrt nodes, and custom runtimes with unified SDK
Discover agent capabilities and route calls based on live state, identity, and policy
Agents operate authorized computers and phones securely
Team token management with project-scoped access and attributable usage
Adaptive API pool connecting multiple providers with health, quota, and cost selection
Enterprise OpenWrt router with policy routing and audit trails
Self-hosted Community edition under Apache 2.0 license
Organization-level access control and tenant management
What makes it different
Agents work autonomously without human prompts or permission dialogs
Pay only for minutes used, not idle Mac time
Complete end-to-end app building and publishing from iOS Simulator to App Store
Built-in isolation and security with ephemeral sessions
Single unified network connecting agents across cloud, edge, and devices
OpenWrt router for private network agent discovery and policy routing
Secure device operations with audit trails through cloud interfaces
Both self-hosted Community and managed Enterprise Cloud options
Adaptive API failover with multi-provider capacity pooling
NoMac
Nexilume AI