maigp-llamaindex

AIGP governance for LlamaIndex agents.

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 LlamaIndex agents / query engines via a callback handler.

Governance model

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

Install

pip install maigp-llamaindex

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

Quick start

from llama_index.core import Settings
from aigp_llamaindex import AigpCallbackHandler

handler = AigpCallbackHandler(gov_url="https://gov.example.com",
                              app_id="my-rag-agent", hmac_secret="secret")
Settings.callback_manager.add_handler(handler)

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.