Enforces budgets for AI agent fleets: verify a signed hash-chained ledger, check spend limits, stop an agent, and issue passports and mandates.
Setup
This project documents no single launch command; follow its repository instructions.
Mandare
mandarelabsOfficial
Related
More- KKepiloleg-vdvAccountability layer for AI agents with passports, per-job mandates and spending limits, an action gateway, a tamper-evident journal and undo.Security5 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
- OOpenWorkProofdengyierVerifiable execution for agent tool calls: authorization, signed policy decisions, evidence chains and offline verification from a SQLite ledger.Security262 Repository stars
- KKakunin MCPKakuninOfficialVerifies an AI agent's X.509 certificate and scope, reads its behavioral risk score and appends events to an immutable audit trail.Security1 Repository stars
- SSignetPrismer-AIProduces Ed25519-signed receipts for agent and MCP tool calls in a local hash-chained audit log that can be verified offline.Security40 Repository stars
- SSafeLine MCPChaitin TechOfficialChinaRead-only access to SafeLine WAF instances, letting agents query attack events through the SafeLine API.Security22.9k Repository stars