Envelope Features Architecture Compliance Specification Get Started Community Contact GitHub
Open Protocol · v1.0 · CC BY-SA 4.0

Every AI agent message
should carry its own trust.

Actions. Routing. State. Identity. Assets. — ARSIA is an open, transport-agnostic envelope protocol that embeds compliance, cryptographic identity, audit, and human oversight into every agent-to-agent message. Not bolted on. Built in.

TLS moved encryption from the application to the transport layer. ARSIA moves compliance from documentation to the message envelope. The difference between telling an agent "be careful with this data" and never letting non-compliant data through in the first place.
$ pip install arsia-protocol
6
Normative docs
7
Compliance profiles
613
Test vectors
31
JSON Schemas
The Core Idea

One envelope. Everything an agent needs to be trusted.

Every message between AI agents is wrapped in a structured envelope that carries cryptographic identity, compliance rules, capability declarations, and audit metadata. The envelope is the protocol. No sidecar, no middleware, no configuration files.

Cryptographic Identity

Every agent has an Ed25519 keypair. Every message is signed. You always know who sent what, and you can always prove it.

Compliance Profile

GDPR, MiFID II, EU AI Act, DORA — the envelope declares which rules apply. Retention, jurisdiction, oversight, PII handling — all explicit.

Audit Trail

Immutable, timestamped records of every interaction. Who did what, when, under which rules. Not an afterthought — a first-class field.

Capabilities & Oversight

Agents declare what they can do. The protocol enforces what they're allowed to do. Human oversight gates are configurable per compliance profile.

Data Residency

Declare jurisdiction at the message level. When data_residency: "EU" is set, messages are routed through compliance brokers whose infrastructure physically resides within the declared zone.

Two-Layer Validation

L1 validates structure against JSON Schema 2020-12. L2 validates semantics: cross-field consistency, compliance rule integrity, temporal logic. Errors are caught before they reach production.

envelope.json
{
  "v": "1.0",
  "type": "request",
  "id": "msg_7f3a...",
  "ts": "2026-05-14T10:30:00Z",

  // Identity — who is talking
  "from": "agent:acme.risk-assessor",
  "to": "agent:acme.compliance-checker",

  // Compliance — which rules apply
  "compliance": {
    "profile": "MIFID-II",
    "retention_days": 1827,
    "data_residency": "EU",
    "human_oversight": "required_before_execution",
    "audit_required": true,
    "pii_involved": true
  },

  // Security — cryptographic proof
  "security": {
    "alg": "EdDSA",
    "kid": "agent:acme.risk-assessor#k1",
    "sig": "base64url..."
  },

  // Payload — the actual message
  "payload": {
    "type": "com.acme.risk-assessment",
    "args": { "portfolio_id": "PF-2847" }
  }
}
Message Intents

Six message types. Every interaction covered.

The protocol defines six intent types that cover the full lifecycle of agent interaction — from requests and responses to human oversight gates and error recovery.

request
Ask another agent to perform an action. Carries capabilities, payload, and compliance requirements.
response
Confirm or deliver results. Correlated to the original request via ID. Carries the same compliance context.
event
One-way notification. No response expected. State changes, alerts, and broadcast updates.
pending_approval
EU AI Act Art. 14. The agent pauses and requests human approval before executing a high-risk action.
approval_decision
Human operator approves or denies. With written justification. The oversight gate that regulators require.
error
Structured errors with 14 standard codes, HTTP status mapping, and retry policies. Not a string — a schema.
Capabilities

Everything you need. Nothing you don't.

The protocol is deliberately opinionated about what belongs in the envelope and deliberately minimal about everything else. Each capability is specified, schema-validated, and tested.

Cryptographic Identity

Ed25519 by default, ES256 and RS256 also supported. Every agent has a verifiable identity. Every message is signed. Key rotation and multi-key support built in.

Spec v1.0

Compliance Profiles

Seven built-in profiles covering GDPR, EU AI Act, MiFID II, DORA, DSA, and PAC Agriculture. Each profile inherits retention, jurisdiction, oversight, and audit rules automatically.

Spec v1.0

Immutable Audit Trail

Every interaction produces a timestamped, tamper-evident audit record. Who did what, when, under which compliance regime. Ready for regulatory inspection.

Spec v1.0

Human Oversight

Configurable gates: required before execution, post-execution review, or within a time window. The protocol enforces them — not your application code.

Spec v1.0

Two-Layer Validation

L1 validates structure against JSON Schema 2020-12. L2 validates semantics: cross-field consistency, compliance rule integrity, temporal logic. Catch errors before production.

Spec v1.0

ECDH-ES Encryption

End-to-end envelope encryption with Elliptic Curve Diffie-Hellman Ephemeral Static. Content is opaque to intermediaries. Only the intended recipient can decrypt.

Spec v1.0

Data Residency

Declare jurisdiction constraints at the message level. EU, US, BR, or any ISO country code. The envelope travels everywhere; the data stays where it must.

Spec v1.0

Capability System

Agents declare capabilities they offer and request capabilities they need. The protocol matches them. An agent can only invoke what it's been granted — structurally enforced.

Spec v1.0

Transport Agnostic

HTTP, WebSocket, message queues, file exchange — ARSIA doesn't care how the envelope gets there. It works above any transport, alongside any agent framework.

Spec v1.0
Architecture

Above MCP and A2A. Complements, doesn't compete.

MCP (Anthropic) handles tool access. A2A (Google) handles agent communication. ARSIA handles the trust layer for both. It sits above transport protocols and below your application — the compliance middleware that was missing from the stack.

Your ApplicationAny agent, any framework
ARSIA ProtocolCompliance · Identity · Audit · Oversight
A2A (Google)Agent-to-agent communication
MCP (Anthropic)Tool & data access
InfrastructureLLMs, cloud, databases

5+1 Architecture

One Core foundation plus five domain primitives — Actions, Routing, State, Identity, Assets — spelling ARSIA.

Zero coupling

Works with any agent framework. No vendor lock-in, no required runtime, no mandatory infrastructure.

3 Conformance Levels

Level 1 (Core): envelope + signing. Level 2: + compliance profiles. Level 3: all five primitives + encryption.

Compliance Profiles

EU-first. Built for everywhere.

Seven normative profiles ship with the protocol, covering Europe's major regulatory frameworks. But the architecture is jurisdiction-agnostic — a compliance profile is a JSON object. If you can define the rules, the protocol can enforce them.

ProfileRegulationRetentionHuman OversightAudit
GDPR-STANDARDGDPR Art. 5, 6Per operatorNot requiredOptional
EU-AI-ACT-HIGH-RISKAI Act Art. 13, 14, 17, 26180 daysRequired before executionRequired
EU-AI-ACT-LIMITED-RISKAI Act Art. 5090 daysNot requiredOptional
MIFID-IIMiFID II Art. 16(7), DORA, PSD25 yearsRequired before executionRequired
PAC-AGRICULTURECAP Reg. 2021/21163 yearsPost-executionRequired
DSA-VLOPDSA Art. 15, 34, 37, 40, 422 yearsWithin 24hRequired
DORADORA Art. 5, 17, 19, 285 yearsWithin 24hRequired
Same architecture, any jurisdiction
HIPAA (US Healthcare) SOX (US Finance) SOC 2 LGPD (Brazil) PIPL (China) APPI (Japan) POPIA (South Africa) PDPA (Singapore) CCPA (California) NIST AI RMF ISO 42001 Your framework
The Specification

Six normative documents. RFC-style rigor.

The ARSIA Protocol specification is a complete, self-contained set of normative documents. Every behavior is defined, every structure has a schema, every rule has test vectors. Built to the standards that standards bodies expect.

ARSIA-Core

Core Envelope

Message structure, EdDSA signing, discovery, authorization, compliance field, transport bindings. The foundation everything else builds on.

ARSIA-Actions

Actions

Capabilities, human oversight (pending_approval / approval_decision), explainability, action registry, rollback semantics.

ARSIA-Routing

Routing

Message routing, compliance broker topology, data residency enforcement, delivery guarantees, idempotency.

ARSIA-State

State

State lifecycle (GET, SET, DELETE, QUERY, PURGE), GDPR obligations (erasure, portability), audit trail generation.

ARSIA-Identity

Identity

Agent identity, certificates, trust levels, 6-phase onboarding flow, JWKS discovery, key rotation.

ARSIA-Assets

Assets

Transaction validation, escrow conditions, asset transfers, MiFID II / DORA / PSD2 controls. Financial intent, not execution.

31
JSON Schemas
613
Test Vectors
100%
Schema Coverage
CC BY-SA
License
Get Started

From pip install to compliant agents in minutes.

The Python SDK gives you the full protocol: envelope lifecycle, signing, validation, compliance profiles, encryption, and CLI tools. Fully typed, zero external dependencies for core features.

1

Install the SDK

pip install arsia-protocol for the library, or pip install "arsia-protocol[cli]" for the command-line tools.

2

Create an envelope

Build a request, response, or event envelope with typed constructors. Set sender, receiver, capabilities, and payload.

3

Sign & validate

Generate Ed25519 keys, sign the envelope, validate against L1 (schema) and L2 (semantic) rules. Three function calls.

4

Apply compliance

Set compliance.profile to any of the 7 built-in profiles. The SDK inherits retention, jurisdiction, oversight, and audit requirements automatically.

5

Ship it

The envelope is transport-agnostic. Send it over HTTP, WebSocket, message queue, or pipe it into MCP/A2A. The protocol doesn't care how — only that it's compliant.

Ed25519 signing ECDH-ES encryption 7 compliance profiles L1 + L2 validation CLI tools Fully typed 14 examples 2 production demos
quickstart.py
from arsia_protocol import (
    create_request,
    generate_ed25519_keypair,
    sign_message,
    verify_message,
    validate_schema,
    apply_profile,
)

# Generate keys
priv, pub = generate_ed25519_keypair()
kid = "agent:acme.bot#k1"

# Build a signed request envelope
envelope = create_request(
    from_agent="agent:acme.bot",
    to_agent="agent:other.svc",
    payload_type="com.acme.analyze",
    capabilities=["com.acme.analyze"],
    args={"data": "ready"},
)
signed = sign_message(envelope, priv, kid)

# Verify + validate
assert verify_message(signed, pub) is True
assert validate_schema(signed) == []

# Apply MiFID-II compliance
signed["compliance"] = {
    "profile": "MIFID-II"
}
enriched = apply_profile(signed)
# retention_days, data_residency,
# human_oversight — all inherited
Community & Governance

Built in the open. Governed by standards.

The protocol is open-source under CC BY-SA 4.0. The SDK is production-ready on PyPI. Standards win through institutional trust and community adoption — we're building both.

GitHub Repository

Full specification source, JSON Schemas, test vectors, and contribution guidelines. Star, fork, or open an issue.

arsialabs/arsia-protocol

SDK on PyPI

Production-ready Python SDK. Envelope lifecycle, signing, validation, compliance profiles, encryption, CLI tools. Fully typed.

pip install arsia-protocol

Examples & Demos

14 examples covering every protocol feature. 2 production demos: fintech securities trade (MiFID II) and healthcare data pipeline (GDPR Art. 9).

Explore demos

W3C Community Group

Member of the AI Agent Protocol Community Group. Shaping the standards for agent interoperability alongside the industry.

Active member

EU AI Pact — Pillar II

Direct channel with the European Commission and AI Office. Building the protocol inside the rooms where the rules are written.

Active participant

Contribute

The spec is open. Propose new compliance profiles, submit test vectors, improve documentation, or build SDK bindings for your language.

Get involved
Get Involved

Join the conversation.
Build with us.

Whether you want to implement the protocol, provide feedback on the spec, or explore commercial tooling — we'd like to hear from you.

Send us a message

Questions about the spec, partnership ideas, or implementation feedback.

Message sent!

We'll get back to you shortly.

🔗 Connect

Reach the team directly, or follow the work on GitHub.
⭐ Star on GitHub
We use no tracking cookies. By submitting a form on this site, you consent to the processing of your contact data to respond to your inquiry, in accordance with GDPR Art. 6(1)(a). Your data is processed by Arsia Labs and is not shared with third parties.