Open-source Agent OS for TypeScript that helps teams operate AI agents like production systems
Human authority infrastructure for autonomous AI
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Open source
Freemium
Pricing
Not given
Free: $0 per month with 2 connections, 1 agent, 500 protected actions per month. Developer: $99/month with 25,000 billable executions included, then $0.001 per billable execution with $500 default overage cap. Business: Contact Sales for paid pilots and enterprise contracts.
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
Cryptographically signed receipts and verifiable evidence
Multi-party approval for organizational authority
Open-source SDK, MCP server, and framework adapters
Authority lifecycle management from grant to revocation
Supported integrations with payments and cloud accounts
Individual, family, business, and enterprise deployment options
Enforcement at tool execution boundaries
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
Write-once signed decisions verifiable by auditors without trusting the vendor
Controls sit at the point where AI systems take consequential actions
One company integrating security and compliance disciplines
Open-source cores and published research allow vendor review
HazelJS
Guardian