Open-source Agent OS for TypeScript that helps teams operate AI agents like production systems
Standing AI teams that run whole business functions around the clock
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
NZ
Pricing model
Open source
Freemium
Pricing
Not given
Free: 200 turns, 1 running team, up to 5 agents. Pay as you go: US$20 buys 2,000 turns. Starter: US$29/month with 2 running teams, up to 15 agents, 5,800 agent turns monthly. Business: US$99/month with 5 running teams, up to 50 agents, 19,800 agent turns monthly. Company: US$399/month with 20 runnin
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
Shadow mode for verification before live operation
Learns from documents, help centres and past tickets
Hard spending caps per team and job
Works with 102+ integrations
Kill switch to stop any team
Approval workflows for risky actions
Team memory and learning across jobs
MCP server and REST API for AI agents
Encrypted credential storage per connection
26+ ready-made teams for different functions
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
Teams learn from your actual business documents and past work, not generic templates
Shadow mode proves capability before autonomous operation
You bring your own model key and pay providers directly, no markup
HazelJS
Jugg.ai