Human-in-the-loop approval UI for AI agent tool calls. Risk-tiered confirmation, drop-in React and Vue components, and a tamper-evident audit trail of every decision. Zero runtime dependencies.
react typescript vue mcp audit human-in-the-loop ai-agents audit-trail tamper-evident risk-scoring hitl langchain vercel-ai-sdk langgraph tool-call copilotkit owasp-llm agent-safety approval-ui
-
Updated
Jun 2, 2026 - TypeScript