The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.
devops mcp workflow-engine nats control-plane governance autonomous-agents ai-safety human-in-the-loop policy-engine audit-trail agent-framework ai-agent llm ai-governance llm-agents agentic-ai ai-orchestration model-context-protocol safety-kernel
-
Updated
Sep 1, 2026 - Go