approval-workflows
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
Local-first CLI for testing whether human approval and intervention controls in AI agent workflows actually work.
Bounded shell and CLI execution for AI agents: structured contracts, policy-gated execution, hardened Linux runtime enforcement, and signed receipts.
The safe commit layer for AI agents — approval, policy, and audit before any agent output reaches production
