Serverless sandboxes that bill only for the seconds your agent's code runs
Stage
Not given
MVP
Founded
Not given
Not given
Based in
US
MX
Pricing model
Freemium
Freemium
Pricing
Free plan with 200 credits per month for public repositories and core features; Pro plan at $16/month ($192 billed annually) with 4000 credits per month and private repository support; Enterprise plan with custom pricing and credits as needed
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
Connect agents with MCP Server for automatic documentation capture
Self-documenting pull requests
Sync existing documentation from Notion, Confluence, Coda, or repositories
Generate documentation on demand
Custom documentation templates
Shared knowledge layer for team-wide agent learning
Integration with Slack and MS Teams for context requests
Analytics dashboards and observability
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
Reduces agent token consumption by 50% through shared knowledge caching
Automatically maintains up-to-date documentation as code changes
Knowledge stays in human-readable Markdown format and is portable
Improves agent consistency across runs with shared knowledge layer
SOC 2 Type II certified for enterprise security compliance
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