AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
위험한 에이전트 행동을 실행 전에 차단하고 휴대폰으로 승인하며, 모든 결정이 서명된 원장에 기록된다
Stop risky agent actions before they run and approve them from your phone. Works with OpenClaw, Hermes, Claude Code, Codex and MCP. Every decision lands in a signed ledger.
개발 도구TypeScript · JavaScriptGitHub @ucsandman온라인운영자 미확인
써 보셨어요? 한 번만 눌러 주세요. 로그인은 필요 없어요.
Remote approvals, policy checks, and execution evidence for unattended AI agents.
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
With a supported enforcement integration, when your AI agent (OpenClaw, Hermes, Claude Code, Codex) tries something destructive or expensive, DashClaw catches it before it runs and asks you first, even when you are not at the keyboard. Every decision lands in a signed ledger.
Run agents unattended without giving them unconditional authority.README 전문 보기 ↗지금 README 전체를 불러올 수 없습니다. 원문 링크에서 읽을 수 있습니다. 아래는 저장된 발췌입니다.
With a supported enforcement integration, when your AI agent (OpenClaw, Hermes, Claude Code, Codex) tries something destructive or expensive, DashClaw catches it before it runs and asks you first, even when you are not at the keyboard. Every decision lands in a signed ledger.
Run agents unattended without giving them unconditional authority.README 전문 보기 ↗