Remote approvals, policy checks and execution evidence for unattended AI agents, logging every decision.
Setup
This project documents no single launch command; follow its repository instructions.
DashClaw
ucsandman
Related
More- CCTRLRunCTRLRunExecution safety gateway for agents: YAML policies allow, hold or deny tool calls, with an approval queue and hash-chained receipts.Security27 Repository stars
- AAgentWardagentward-aiProxies MCP tool calls and enforces least-privilege YAML policies, flags PII and PHI, detects risky skill chains and logs an audit trail.Security19 Repository stars
- AAssayRul1anPolicy proxy for MCP tool calls that denies risky calls and records decisions in offline-verifiable evidence bundles.Security13 Repository stars
- SScopeBlind GatewaytomjwxfWraps MCP servers with per-tool Cedar policies, approval gates and optional signed receipts, in log-only or enforce mode.Security11 Repository stars
- AAgent Passport MCPaeoessOfficialIssues agent passports, verifies scoped delegation chains, enforces gateway policy and emits signed records.SecurityLocal + remote4 Repository stars
- CCSL CoreChimera ProtocolDiscovers AI agents on a machine and what they can reach, verifies safety policies with Z3 and TLA+, and enforces them deterministically.Security27 Repository stars