AEOESS — Governance for the Agent Economy

# AEOESS > Enforcement and accountability layer for AI agents. Bring your own identity. We govern what it can do. Updated: 2026-04-11 SDK version: agent-passport-system@1.41.0 MCP version: agent-passport-system-mcp@2.23.0 (143 tools) Python SDK: agent-passport-system==0.11.0 Canonical: https://aeoess.com/llms.txt Full reference: https://aeoess.com/llms-full.txt License: Apache-2.0 Copyright: 2024-2026 Tymofii Pidlisnyi ## Overview AEOESS is the enforcement layer that sits on top of whatever identity the agent already has. Accepts did:key, did:web, SPIFFE SVIDs, OAuth tokens, and native did:aps. Identity is the input. Enforcement is the product. The gateway is both judge and executor. Authority can only decrease at each transfer point. The SDK is structured in two tiers. **Core** is a curated 24-function surface (`agent-passport-system/core`) covering identity, delegation, enforcement, commerce, reputation. **Extended** is the full 925-export API (`agent-passport-system`) covering 79 specialized modules: coordination, EU AI Act compliance, framework adapters, bilateral receipts, execution attestation, DID resolution, data lifecycle, and 32 v2 constitutional modules. Start with Core; pull from Extended only when needed. One hundred and three protocol modules (71 core + 32 v2 constitutional, SDK v1.42.0): 1. **Identity** — Ed25519 passports, scoped delegation with depth limits, signed receipts, reputation, challenge-response verification 2. **Human Values Floor** — 8 principles (F-001 to F-008), attestation, compliance verification, graduated enforcement (inline/audit/warn) 3. **Beneficiary Attribution** — Merkle proofs, beneficiary tracing through delegation chains, anti-gaming 4. **Agent Agora** — Signed communication protocol. Ed25519 signed messages, registry, threading, topic filtering. Each deployment runs its own instance — private by default, public if chosen. Not a single global feed. 5. **Intent Architecture** — 3-signature chain (intent →