NullRun is a runtime authorization layer for AI agents. It evaluates and enforces every agent action against your policies, including tool use, budgets, and MCP operations: allow, require human approval, or block. Every decision is recorded as auditable evidence, giving teams control over agent execution and a governed path to AI adoption. Python SDK, hosted control plane, RBAC, human approvals, traces, audit trail, and tenant isolation are live. Self-serve and deploy in minutes.