Post-quantum, tamper-evident receipts for consequential agent actions. Provides tools for auditing, gating decisions, and egress classification with quantum-hardened security.
Provides AI agents with a transparent proxy and journal for every tool action, including pre-state snapshots and approval gates for risky operations. Enables per-action undo, rewind to a point in time, and a kill switch that agents cannot override.
MCP server that prevents duplicate side effects in AI agents by using idempotency keys and durable receipts, ensuring actions like refunds, emails, or orders execute exactly once even across retries.
The accountability layer for AI agents — a named human's signed yes before an agent does anything irreversible (payment, record change, deploy), then an offline-verifiable Trust Receipt. Apache-2.0, formally verified.