What we have learned running agents that run agents
Papers from the Vorim team on identity, permissions, audit trails and governance for AI agents. Free, in exchange for an email.
Quantum computing and cryptographic identity for AI agents
Every signature behind today's AI agent identities uses maths a large quantum computer could break. No such machine exists yet, but the cost of building one keeps falling, and signed agent evidence has to stay believable for years. This paper separates what quantum computing has demonstrated from what is claimed or disputed, sets out what breaks in an agent identity stack, explains why quantum key distribution does not help identity, and gives six rules for quantum-ready agent identity.
Read and downloadGroup identity, charters and attestation for AI agent swarms
Every identity standard names the agent. None names the group. When an orchestrator delegates to three workers and one spawns two more, every question an operator or auditor asks is about the six together. This paper gives the group a name the server mints, a charter that is enforced, a budget that conserves, a stop whose propagation is measured and whose limits are stated, and a 24-hour signed attestation a counterparty can verify offline.
Read and download