# AIR Blackbox

> The trust infrastructure between human intent and AI execution. Verify. Filter. Stabilize. Protect.

AIR Blackbox is open-source trust infrastructure that sits inside every AI call -- between your team and the AI stack -- providing decision traceability, escalation intelligence, operational drift detection, and human oversight proof. v1.13.0. Runs locally. Apache 2.0.

AI made generation abundant. What becomes valuable now is the infrastructure that verifies, routes, constrains, and records machine-assisted work in real time. Compliance is the wedge. Trust infrastructure is the platform.

## Why AIR Blackbox

Enterprise governance platforms (Credo AI, Holistic AI, OneTrust) audit after the fact. AI security firewalls (Arthur AI, Lasso, Lakera) filter threats. AIR Blackbox sits inside the call -- at the interception layer between human intent and AI execution. That gives you:

- **Verify** -- HMAC-SHA256 tamper-evident audit chains for decision traceability
- **Filter** -- PII detection and prompt injection scanning in real time
- **Stabilize** -- 51 compliance checks in CI/CD for operational drift detection
- **Protect** -- Human oversight attestation (Art. 14 delegation logging)

Tombstone is the enforcement companion: it wraps an agent's dangerous tools and blocks destructive actions (delete, drop, overwrite) before they run, sealing every decision to a tamper-evident ledger. AIR Blackbox records and proves; Tombstone prevents.

## Key Links

- [Homepage](https://airblackbox.ai)
- [GitHub](https://github.com/airblackbox/airblackbox)
- [Tombstone (agent action firewall, blocks and proves destructive agent actions)](https://github.com/airblackbox/tombstone)
- [PyPI](https://pypi.org/project/air-blackbox/)
- [Audit Chain Specification (Open Standard v1.0.0)](https://airblackbox.ai/spec)
- [CI/CD Integration Guide](https://airblackbox.ai/ci-cd)
- [Compliance Mapping](https://airblackbox.ai/compliance-mapping)
- [Blog](https://airblackbox.ai/blog/)

## Installation

pip install air-blackbox

## Quick Start

air-blackbox comply --scan . -v

## Features

- 51+ EU AI Act compliance checks across Articles 9, 10, 11, 12, 13, 14, 15
- Article 12 Compliance Layer -- static + runtime analysis for tamper-evident logging
- Receipt signing for independent verification: Ed25519 by default; ML-DSA-65 (FIPS 204) post-quantum option in the gateway
- HMAC-SHA256 tamper-evident audit chains (open standard)
- Self-verifying .air-evidence bundles for auditors
- Prompt injection detection (20 patterns, 5 categories)
- GDPR scanner (8 checks)
- Bias and fairness scanner (6 checks)
- ISO 42001 + NIST AI RMF + Colorado SB 24-205 crosswalk
- Trust layers for LangChain, CrewAI, OpenAI SDK, Claude Agent SDK, Google ADK, AutoGen, Haystack
- Agent-to-agent (A2A) compliance protocol
- Pre-commit hooks
- MCP server integration
- Runtime validation engine (tool allowlists, content policy, PII output scanning)

## Quality

- 180+ tests across the Python SDK and Go gateway
- Lint and format enforced in CI (ruff)
- Zero lint warnings (ruff E/F/W/I rules, CI-enforced)
- Consistent formatting (ruff format, CI-enforced)
- Integration tests for LangChain, OpenAI SDK, CrewAI
- CI matrix: Python 3.10, 3.11, 3.12



## License

Apache 2.0

## EU AI Act Deadline

EU AI Act high-risk obligations (Annex III, including hiring AI) were deferred to December 2, 2027 under the Digital Omnibus agreement. Transparency obligations remain on the August 2, 2026 schedule.