air-blackbox 1.13.0

AI governance control plane - compliance, inventory, incident response, and audit for AI agents

AIR Blackbox

AI governance control plane - compliance, inventory, incident response, and audit for AI agents.

Install

pip install air-blackbox

With framework support:

pip install air-blackbox[langchain]    # LangChain trust layer
pip install air-blackbox[crewai]       # CrewAI trust layer
pip install air-blackbox[openai]       # OpenAI Agents SDK trust layer
pip install air-blackbox[all]          # Everything

Four Commands

air-blackbox comply      # EU AI Act gap analysis, scans your code
air-blackbox discover    # Shadow AI inventory + AI-BOM generation
air-blackbox replay      # Incident reconstruction from audit chain
air-blackbox export      # Signed evidence bundle for auditors

Quick Start

from air_blackbox import AirBlackbox

air = AirBlackbox()
client = air.wrap(openai.OpenAI())
# Every LLM call is now HMAC-logged through the gateway

With framework auto-detection:

from air_blackbox import AirTrust

trust = AirTrust()
trust.attach(your_langchain_agent)
# Framework auto-detected. Audit trails active.

What It Does

Command	What You Get
comply	Per-article EU AI Act gap analysis (Art. 9-15) from a static scan of your code
discover	AI-BOM (CycloneDX), shadow AI detection, model version tracking
replay	Full incident reconstruction, HMAC chain verification
export	Signed evidence package: compliance + AI-BOM + audit chain

Signing and verification

The audit chain is HMAC-SHA256 on every install. Receipts are signed for independent third-party verification with Ed25519 by default (install air-blackbox[gate]). ML-DSA-65 (FIPS 204) post-quantum signing is available in the gateway. The bundled verify.py checks the HMAC chain using only the Python standard library.

Links

• Website: airblackbox.ai
• Gateway: github.com/airblackbox/airblackbox
• Docs: gateway/docs
• License: Apache-2.0