GuardClaw – cryptographically verifiable execution logs for AI agents
Cryptographically chained audit logs for AI agents; offline verification means no SaaS lockdown.
Protocol Specification
Another signed claim spec when JWT and Verifiable Credentials already exist.
Developers building decentralized identity or authorization systems
JWT · W3C Verifiable Credentials · Macaroons
Cryptographically chained audit logs for AI agents; offline verification means no SaaS lockdown.
OAuth + TLS for AI agents with Ed25519 identity and global kill switch before agents act.
Cosign for AI agents: cryptographically signed receipts for every agent action.
Signed receipts for AI agent actions solve an accountability problem that didn't exist before MCP.
Protocol spec without a working notarization service or verification tool.
OAuth + TLS for AI agents—eight-step verification pipeline, but adoption depends on framework integration.