deployment-safety
🚪 Governance gate for AI agents. Enforce policies before deployment: request contracts, operational safeguards, identity boundaries, action budgets. CLI tool with YAML config, JSON/text output, CI/CD integration.
MCP server for safe AI agent runtime upgrades — version-aware regression catalog, pre/post snapshot diff, rollback guides. Read-only advisor: never executes upgrades. Bring your own catalog for non-OpenClaw runtimes.
