Serverless sandboxes that bill only for the seconds your agent's code runs
macOS sandboxes for AI agents and CI
Stage
MVP
Not given
Founded
Not given
Not given
Based in
MX
Not given
Pricing model
Freemium
Free trial
Pricing
Shark Pro $5/month includes $5 of usage; Shark Studio $25/month includes $25; Shark Scale $100/month includes $100. Commands run at $0.12 per compute-hour, billed per second only while running. Services: 2 vCPU / 2 GiB at $0.03/h; 4 vCPU / 4 GiB at $0.06/h. Storage $0.08/GiB-month with first 5 GiB f
$1.10 per hour, billed by the second with no minimum. $5 in free credit to start.
Key features
Persistent Space for agent files and databases
Pay only for compute time while command runs, not idle or thinking time
HTTP API with Python and TypeScript SDKs
CLI for devbox with Claude Code and Codex support
Sleeping services that wake in milliseconds
Fork Spaces fast without booting VM
API key isolation outside VM with egress proxy
Fast file search with sharkfn 300–600× faster than ripgrep
Integration with LangChain, LangGraph, smolagents, and Prefect
macOS sandboxes created and controlled over HTTP API
Build and test with Xcode and Swift
GitHub Actions integration with offstage-macos runner
Desktop access and GUI app support
iOS Simulator ready to use
File read and write operations via API
Up to 4 concurrent CI jobs per team
Mac Studio M5 Max hardware
What makes it different
Billing only for seconds code actually runs, not idle or thinking time
Lowest cost compared to alternatives for agent infrastructure
Persistent Storage with fast Space fork and file access without VM boot
No GPU required, works with unmodified existing agent harnesses
Sleeping services wake in milliseconds with zero idle billing
Pay only for the time you use, billed per second with no 24-hour minimum
$1.10 per hour, significantly cheaper than competitors like GitHub Actions ($3.72/h) and AWS EC2 Mac ($29.52/day)
$5 in free credit to try the service with no credit card required
Fresh macOS sandbox for each CI job, no state carried between runs