Self-hosted multi-agent simulation framework for building autonomous agent civilizations
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
Not given
Freemium
Pricing
Developer License: $49 USD (one-time) includes Python/FastAPI engine source code, Vite/React observer dashboard, zero-cost mock mode, and single-user research grant. Commercial License: $149 USD (one-time) includes everything in Developer License plus perpetual royalty-free commercial distribution,
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
Decoupled tick loop with independent tick rate scheduling
SQLite WAL-mode persistence with concurrent reads and zero lock overhead
Multi-generational genealogy and asset transaction logs
Zero-token mock mode for local simulation without API costs
Python/FastAPI backend with Vite/React observer dashboard
Circadian cycles and natural mortality mechanics
Seamless LLM integration with OpenAI, Anthropic, or Ollama
Docker Compose deployment stack for Commercial License
Instant source code delivery with digital license key
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
Turnkey engineering for complex simulations without building the loop from scratch
Zero recurring platform subscriptions with direct software licensing
No lock overhead persistence with WAL-mode SQLite for concurrent reads
Local LLM execution without incurring API costs in mock mode
Royalty-free commercial distribution rights with Commercial License
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
Morgul Engine