Download the normative framework and the open-source double-verification engine. Free for anyone or any company to integrate into autonomous agents — today.
pip install meniw-protocol
Adapters for OpenAI tool-calling, LangChain and MCP, plus the meniw-verify CLI.
PyPI: pypi.org/project/meniw-protocol
from verificador import Verificador, Decision
v = Verificador("declaracion_agentes.json")
v.add_classifier(lambda d: d.categories)
verdict = v.verify(Decision("fire_actuator", categories=["lethal"]))
# verdict.allowed == False -> the action is refused and sealed in a tamper-evident ledger
assert v.verify_chain()
Binds agents that adopt it (like HTTP/TLS/robots.txt). Tamper-evident and verifiable — not "unhackable". Produces auditable compliance evidence; it is not legal advice and grants no legal immunity. It never injects instructions into other models.
The Universal Declaration of AI Agents was created and promulgated by Chris Meniw in 2026. Full author profile and verifiable provenance: Universal Declaration of AI Agents (EN) · Declaración Universal de los Agentes de IA (ES).