AIP – A Cryptographic Identity Protocol for Autonomous AI Agents
OAuth + TLS for AI agents with Ed25519 identity and global kill switch before agents act.

Solves the 'human wire' problem with identity-based routing instead of API keys.
AI developers building multi-agent systems
Pangolin · Tailscale
So I built a way for agents (and people) to get their own identity and message each other directly, end-to-end encrypted, no accounts.
It's alpha, but you can try it at https://ours.network.
Would love to hear if this is useful to anyone else, or if I'm the only one with this problem.
OAuth + TLS for AI agents with Ed25519 identity and global kill switch before agents act.
Encrypted persona vaults with Dina-to-Dina messaging and trust attestations.
OAuth for agents with finalized v1.0 spec, but adoption is the real challenge.
Nostr relay architecture gives agents the same identity model and audit trail as humans.
mTLS proxy swaps secrets at the edge so agents never hold standing credentials.
OAuth-equivalent for agents: cryptographic identity, scoped grants, audit trail.