GitHub Repository

Open-source EU AI Act compliance scanner. 51 checks across Articles 9-15. Drop-in trust layers for LangChain, CrewAI, AutoGen, OpenAI. Local-first, no data leaves your machine.

17 starsPython

Air – Open-source black box for AI agents (tamper-evident audit trails)

Name: Air – Open-source black box for AI agents (tamper-evident audit trails)
Availability: InStock
Author: shotwellj

by shotwellj·Feb 18, 2026·2 points·1 comment

Visit Project View on HN

AI Analysis

●●SolidBig BrainWizardry

Cryptographic audit chain for agents, but lacks observability dashboards competing tools provide.

Strengths

•Tamper detection via HMAC-SHA256 chain is a real differentiator vs. mutable observability logs
•One-line integration (air_wrap) makes adoption frictionless for existing OpenAI SDK codebases
•Interactive demo + multi-provider test suite (30 tests, 8 LLM providers) proves production readiness

Weaknesses

•Solves auditability but ignores performance observability; complements rather than replaces tools like Langfuse or Helicone
•Custody of audit trails (MinIO vault) adds operational complexity vs. managed alternatives

Similar Projects

Security●●Solid

Air – Open-source black box for AI agents (tamper-evident audit trails)

Instead of another observability dashboard, this project builds a provable audit trail: an OpenAI-compatible reverse proxy that vaults prompts in MinIO and links calls with an HMAC-SHA256 tamper-evident chain, plus replay tooling (replayctl) and Jaeger traces. The cryptographic audit chain and the one-line SDK wrap are clever and practical; the real operational work left to teams will be key management and storage/retention strategy.

WizardryNiche Gem

shotwellj

213mo ago

Security●●Solid