AIR Blackbox
Tamper-proof audit trails for every AI agent call
What it does
Your AI agents make thousands of calls but can you prove what they said? AIR Blackbox is an open-source reverse proxy that records every LLM call with HMAC-SHA256 chaining. If anyone tampers with a record, the chain breaks instantly. Unlike observability tools, AIR focuses on provability: - Cryptographic audit chain for tamper-proof integrity - EU AI Act compliance (Articles 9-15) - PII detection and prompt injection scanning - Shadow AI detection via model registry pip install air-blackbox
Does the same job
all alternatives →
- LFLockbox: forward proxy for making third party API calls2024 · github.com · ▲137
Project AIR by VindicaraMay 2026 · vindicara.io · ▲9Open source SDK for AI agent governance and audit
DecisionBox EnterpriseApr 2026 · decisionbox.io · ▲67Agent that writes SQL for you to validate database insights
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
