Independent counterparty evidence checks before autonomous transactions
AUX is a machine-native API that certifies whether an AI agent has enough independently verified evidence to proceed with a consequential action. It checks public business identity and sanctions sources, can validate signed private-source attestations, and returns signed certification receipts for downstream systems to evaluate.
Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 13 September 2026.
Is this your tool? Claim this listing to manage your content and analytics.
Ask about AUX
Get answers based on AUX's actual documentation
Try asking:
About
AUX is agent infrastructure for pre-action counterparty verification. It is aimed at developers, agent platforms, and organizations building autonomous systems that need an evidence-based control step before actions such as vendor payments or other consequential transactions.
AUX is a verification and trust-control layer, not a general-purpose agent and not a payment-execution system. Its clearest value is separating an agent's own assertions from independently resolved or verified evidence, then attaching provenance and...
Executes tasks you assign, one step at a time, within narrow domains.
Dimension Breakdown
Categories
Ask about AUX
Try asking:
When AUX changes its pricing, we catch it the next morning
We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.