Open-source Agent OS for TypeScript that helps teams operate AI agents like production systems
Controlled database access and security layer for AI agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
ES
Pricing model
Open source
Freemium
Pricing
Not given
Free tier: 30 successful calls per month. Pay Per Use: Managed AI €0.10 per question, BYOK €0.02 per question, Guard €0.01 per check. Enterprise: custom pricing.
Key features
Durable execution with crash-safe HITL
Agent DNA for versioning agents as packages
Gatekeeper default-deny authorization
Skillgate capability curation
Local-first deployment without Kubernetes requirement
Agent VM with effect typing and speculation
Decision Runtime for bounded closed-set judgment
Organism for multi-agent coordination
Routes - define tables and columns agents can query with plain-language guides
Guard - check and approve every INSERT, UPDATE, or DELETE before execution
Read-only database connections with role-based access
REST API, MCP, and A2A protocol support
Support for Postgres, MySQL, MariaDB, and Supabase
Typed multi-question answers in one request
Data Map generation and review
Full query tracing and audit logs
BYOK - Bring your own LLM key from OpenAI, Google, Anthropic, or xAI
What makes it different
Agents live in the same TypeScript DI app as your APIs, not as separate services
Production-ready without cloud or Kubernetes dependency
Complete operating system, not glue between frameworks
Agents pause, resume, and survive restarts in production
Developer-first with decorators and DI patterns developers already know
No data copying - agents query your database where it lives, data never moves
No code needed - set up routes, agents, and Guard rules through the dashboard without YAML or coding
Per-agent access control with clearcut boundaries
Exact rule enforcement with no model-based decisions at check time
Pay-per-success billing - you only pay for successful queries
HazelJS