Source control for coding agents with conflicts settled before code exists
Open-source Agent OS for TypeScript that helps teams operate AI agents like production systems
Stage
Startup
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Open source
Pricing
Free: $0 for up to 3 projects and one person (never charges). Builder: $15 a month or $150 a year. Team: $36 per person a month or $360 per person a year. New accounts start on Team for 14 days free with up to 5 projects.
Not given
Key features
Agents declare plans before writing code
Written rules automatically settle conflicting plans
Integration with Claude Code, Codex, and MCP clients
GitHub repository mirroring after each merge
Intent-based workflow instead of pull requests
Drift detection comparing code changes to declared plans
No branch names; work identified by intent number
Write rules per folder with CI files people-only
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
What makes it different
Conflicts settled before any code is written
Agents review intent goals and plans, not line-by-line diffs
Works with your existing agents without leaving GitHub
Only humans approve merges, never agents or models
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
gitring
HazelJS