| Summary | Human sign-off + trust receipts for AI agents: requires a named human's approval before an irreversible action (payment release, record change, deploy), then mints an offline-verifiable Ed25519 Trust Receipt. Also exposes trust profiles, receipt verification, disputes, and delegation. Apache-2.0; policy engine formally verified. Install: npx -y @emilia-protocol/mcp-server. | Policy enforcement for AI coding agents derived from existing instruction files (CLAUDE.md, .cursorrules, .windsurfrules, .github/copilot-instructions.md) — no separate YAML to maintain. Rules with prohibitive predicates (never, forbids, mustnot) emit permissionDecision: deny to block tool calls in Claude Code; advisory rules inject context. PostToolUse is correlated with PreToolUse to produce per-rule obeyed/ignored compliance verdicts in a local JSONL audit log. MCP tools — araiaddguard (register rules mid-session), arailistguards, arairecentdecisions — work in any MCP client (Claude Desktop, Cursor, Windsurf, Cline). No network on the hook hot path; opt-out anonymous telemetry. |
|---|