Enforces rules from agent instruction files such as CLAUDE.md by blocking prohibited tool calls, with an audit trail and per-rule compliance stats.
Setup
This project documents no single launch command; follow its repository instructions.
Ārai
Taniwha AI
Related
More- AAI Runtime GuardruntimeguardRuntime policy enforcement for AI agents that prevents accidental system damage and unauthorized access, with automatic backups before file writes.Security15 Repository stars
- 火火山引擎云审计 CloudTrail MCP火山引擎OfficialChinaCall the Volcengine CloudTrail audit service in natural language to look up audit events.Security330 Repository stars
- EEMILIA ProtocolEMILIA ProtocolRequires a named human's approval before irreversible agent actions such as payments or deploys, then issues an offline-verifiable Ed25519 receipt.Security599 Repository stars
- DDashClawucsandmanRemote approvals, policy checks and execution evidence for unattended AI agents, logging every decision.Security313 Repository stars
- OOpenWorkProofdengyierVerifiable execution for agent tool calls: authorization, signed policy decisions, evidence chains and offline verification from a SQLite ledger.Security262 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