# Ratify Agent Relay Harness

> Offline, one-command reproduction harness + adversarial annex for the Agent Relay x Ratify Phase 2 flagship.

- **Website:** https://github.com/identities-ai/ratify-agent-relay-harness
- **Pricing:** unknown
- **Categories:** AI Agents, Developer Tools
- **Tags:** ai-agents, developer-tools, writing-content
- **Platforms:** CLI
- **Last verified:** 2026-08-26
- **Canonical page:** https://linkrena.com/tools/ratify-agent-relay-harness

## About

and revoked while the work was still running. This repository replays that offline so you can

published claim fails to re-verify. No network call to either company.

What Ratify is. An open protocol for delegated authority that is bounded to a named

it. The receiving side checks who authorized what, for how long, and whether it still stands,

This is the Ratify-Protocol-side reproduction harness and adversarial annex. It orchestrates

does not reimplement them. The path-traversal and two-principal-isolation cases need two OS

single unprivileged uid, so they SKIP here and the annex reads six refusals rather than eight.

The one-command reproduction of the engagement ( npm run engagement ), offline, exits non-zero if any published claim fails to re-verify.

The published evidence trail for that offline run: the delegation chain, every ProofBundle , the VerificationReceipt chain, and a verifier-signed head checkpoint committed under evidence/ .

The adversarial annex ( adversarial/ ): runnable failing tests a skeptic can run.

Everything under evidence/ is a synthetic model of the engagement, built so that someone with neither deployment can run it. Its identifiers are fixtures: demo-cert-root , a demo channel id, fixed timestamps. Nothing in here is a certificate that was issued during the live sessions of 18 and 19 August 2026.

## Related tools

- [Hexstrike AI](https://linkrena.com/tools/hexstrike-ai): HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pent…
- [CAIPE](https://linkrena.com/tools/caipe): Open-source multi-agent system for AI-powered platform engineering.
- [Latticedb](https://linkrena.com/tools/latticedb): Embedded single-file knowledge graph database with vector search and full-text search for AI/RAG apps - jeffhajewski/latticedb
- [CarWatch](https://linkrena.com/tools/carwatch): Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI.
- [Texbrain](https://linkrena.com/tools/texbrain): FOSS browser-based LaTeX editor with live preview, on-demand packages and git integration.
- [Tako VM](https://linkrena.com/tools/tako-vm): Tako VM is a secure file system and Python execution layer for AI agents: gVisor-isolated Docker containers with job queues, workers, retries, and replay.