Quickstart
Compliance for your AI agents in 5 minutes.
One pip install, four commands, 89% automated. No Docker, no config, nothing leaves your machine.
One pip install, four commands, 89% automated. No Docker, no config, nothing leaves your machine.
pip install air-blackbox
Generates sample AI agent records and runs a compliance check. No Docker, no config.
air-blackbox demo
→ Creates 10 sample .air.json records (4 models, 3 providers)
→ Generates RISK_ASSESSMENT.md + DATA_GOVERNANCE.md templates
→ Runs EU AI Act compliance check: Articles 9–15
air-blackbox comply -v
Shows per-article status with detection type (AUTO/HYBRID/MANUAL) and fix hints for every failing check.
air-blackbox discover
Shows every model, provider, and API endpoint your agents are using. Shadow AI detection built in.
For live traffic analysis with HMAC audit chains, tamper-proof logging, and real-time compliance:
git clone https://github.com/airblackbox/airblackbox.git
cd gateway
cp .env.example .env # add your OPENAI_API_KEY
docker compose upThen point your LLM client at the gateway:
from openai import OpenAI from air_blackbox import AirBlackbox air = AirBlackbox() client = air.wrap(OpenAI()) # Every LLM call is now HMAC-logged through the gateway
EU AI Act compliance from live gateway traffic. Checks across Articles 9–15.
Shadow AI inventory + AI-BOM generation. Every model, tool, and provider cataloged.
Incident reconstruction from the tamper-proof audit chain. Full agent timeline.
Signed evidence bundles for auditors and insurers. One command, one document.