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: Personal memory up to 1,000 records with no time limit. Pro: $5 per month or $50 per year for unlimited personal memory. Team: $10 per month plus $5 per member per month for shared memory and collaboration.
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
Personal and team memory
MCP server with OAuth 2.1 or token authentication
Search by words and by meaning
Record provenance and version history
Conflict detection and resolution
JSON export and import
Project-based organization with hierarchical grouping
Urgent inbox for team notifications
Role-based access control for teams
Works with Claude, ChatGPT, ZCode, Grok and other MCP 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
One memory accessible from any AI assistant without re-explanation or chat copying
Separate personal and team memory layers with no automatic sharing
Records show full history and cannot be silently erased or replaced
Search by meaning finds relevant records even with different wording
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