Human approval for AI agents. `request_human_approval(action, context, risk)` pauses a high-stakes action (refund, payo…
Human approval for AI agents. `request_human_approval(action, context, risk)` pauses a high-stakes action (refund, payout, deploy, deletion) until a named person approves or rejects in the console, by email, Telegram or Slack. Silence is not consent: a timeout, expiry or rejection returns approved=false. Every decision is sealed in a hash-chained audit log you can export. EU-hosted (Germany), DPA available. Free sandbox key (100 approvals/month): https://raposa.group/start/
agentlabbusiness
mcp
free
Others in the same category, ranked by how often they are opened.
