Serverless sandboxes that bill only for the seconds your agent's code runs
Shared context platform for human-agent teams
Stage
MVP
Startup
Founded
Not given
2026
Based in
MX
US
Pricing model
Freemium
Freemium
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
Starter: Free (all features and integrations). Advanced: Bespoke pricing (includes onboarding, training, custom integrations). Enterprise: Bespoke pricing (includes rollout plan, configurable data retention, security controls).
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
Real-time context capture from conversations and decisions
Agent priming with team context
Team status and live activity visibility
Search and retrieval across team knowledge
Meeting capture and decision recording
Coordination signals (murmurs) between team members
Human-agent handoffs without re-briefing
Ox Plans for architectural documentation
Integration with multiple AI coding tools
iPhone and Apple Watch app for capturing thinking
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
Persistent context that moves with work instead of starting from scratch
Context layer independent of any single tool or ecosystem
Prevents drift and duplication across human-agent teams
Free for small teams with all features included
Data portability: context can be exported and kept as git repos