Quantum computing and cryptographic identity for AI agents

What quantum computers can and cannot do in 2026, and how to keep agent evidence trustworthy

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.

• A plain table of 2024 to 2026 quantum results, sorted into demonstrated, vendor-reported and disputed
• How the cost of breaking RSA and the elliptic curves agents sign with fell in eighteen months
• Which parts of an agent identity stack break, ranked by how long their evidence must last
• Why "trust now, forge later" matters more for agents than "harvest now, decrypt later"
• Six rules for quantum-ready agent identity, and an honest statement of where Vorim stands

1. Executive summary
2. Where quantum computing really is, October 2026
3. What quantum computers have usefully solved so far
4. The cost of breaking today's keys is falling
5. What breaks in an agent identity stack
6. Trust now, forge later
7. Quantum technologies and identity
8. Standards and timelines
9. The road to 2035
10. Six rules for quantum-ready agent identity
11. Where Vorim stands

9 pages, 22 min read. Published for Cybersecurity Awareness Month, October 2026. May be shared and quoted with attribution.