Source control for coding agents with conflicts settled before code exists
Stage
Not given
Startup
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Not given
Pricing
Local: free with CLI, SDK, local proxy, and MCP wrapper. Founding Team: $499 per month after a 30-day pilot, including guided setup, hosted approvals, team dashboard, verified ledger sync, and direct support.
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.
Key features
Exact payload binding and hash verification
Policy engine with Cedar and Rego support
Local enforcement proxy and CLI
Hosted approvals dashboard and team coordination
Verifiable action ledger with audit trail
Model Context Protocol wrapper
Support for GitHub, Slack, Linear, Jira and cloud platforms
Runtime integration with Anthropic, OpenAI and Cursor
Credential-free playground and examples
ActionPass signed authorization artifact
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
What makes it different
Payload approval bound to exact hash, not summary—changes after approval are automatically rejected
Local enforcement with credential-free operation before team coordination layer
30-day pilot model with no long-term commitment required
Open-source ActionPass artifact and verifier for transparency
Adapter-side verification prevents tool execution after payload tampering
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