maigp-openai

AIGP governance for direct OpenAI Chat Completions calls.

Part of MAIGP — the Mediated AI Governance Protocol: a runtime consent / scope / evidence layer for AI systems. Every governed call is CHECKed before it runs (policy, scope, jurisdiction, circuit-breaker) and RECORDed + TRACEd as tamper-evident evidence after.

What it governs

Governs raw openai client calls (Chat Completions API).

Governance model

This adapter maps the framework's lifecycle onto the AIGP agent-governance loop provided by maigp-agent-core:

Install

pip install maigp-openai

Pulls in maigp-agent-core (shared lifecycle) and, transitively, maigp-client.

Quick start

from openai import OpenAI
from aigp_openai import GovernedOpenAI

governed = GovernedOpenAI(client=OpenAI(),
                          gov_url="https://gov.example.com",
                          app_id="my-openai-app", hmac_secret="secret")
response = governed.chat("gpt-4o", [{"role": "user", "content": "Hello"}])

Raw API vs agent loop

This wraps single Chat Completions calls. To govern the OpenAI Agents SDK agent loop (Runner, tools, handoffs), use maigp-openai-agents.

Links

• Protocol, specs & full adapter catalog: https://github.com/owner-spec/aigp-protocol
• Issues: https://github.com/owner-spec/aigp-protocol/issues

License: Proprietary. © Kanjani AI Research & Causum.