Serverless sandboxes that bill only for the seconds your agent's code runs
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
MX
Pricing model
Freemium
Freemium
Pricing
Free: $0 per month for 1 user. Pro: $19/month for up to 10 members. Enterprise: custom 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
Key features
Run multiple coding agents in parallel on separate git worktrees and branches
Task board with live terminals for each agent session
Access Profiles to control permissions for each agent
Integration with 100+ providers
Audit logs of all agent actions and refusals
Self-hostable access layer
On-demand GPU compute by the second
Local-first execution keeping source code and output on user's machine
Support for Claude Code, Codex, and other agentic clients
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
What makes it different
Open-source access layer under Apache-2.0 so you can read the security model
Enforce access permissions at the system level, not through prompts
Centralized access control across all agents and platforms simultaneously
Keep data portable with plain files on your own disk, no vendor lock-in
Complete audit visibility of what every agent accessed and was denied
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