Antonio's profile on Product Hunt

About

What Axiom governs → Agent actions & tool calls — checked before they execute → Intent & risk — classified in microseconds, no LLM on the hot path → Outputs & data — PII and policy gating → Human oversight — one-click approvals + a named-owner kill switch → The audit trail — cryptographically signed, provable to a regulator Built for regulated industries — financial services, insurance, healthcare, and government, where "it probably complied" isn't an answer. Mapped to the frameworks that matter — the EU AI Act (most obligations enforceable August 2026), the OWASP LLM Top-10, and the NIST AI RMF — turned into checklists an engineer can actually follow, not a policy nobody reads. Live at runaxiom.orivael.dev also checkout · 25 governance tools over MCP · NVIDIA Inception member.

Badges

Tastemaker

Gone streaking

Gone streaking 5

Maker History

OrivaelThe control plane for AI agents — govern before they act

🎉

Joined Product HuntJuly 1st, 2026

Forums

•

1mo ago

NodeXLoop — Agent Loop DevTools - Debug AI agents like you debug code

A visual debugger for AI agent loops, inside VS Code. Build Agent → tool → critic → retry → gate → test → approve on a canvas, run it node-by-node with breakpoints, and see exactly which call the guard blocked and why. The graph is a .loop.yaml next to your code, so it reviews in the same PR. Axiom guard on by default: a stalled critic loop drops from 20 model calls to 6, a prompt injection costs 0. 37 templates, org review (local preview), audit export. Free on the Marketplace and Open VSX

•

3mo ago

Orivael - The control plane for AI agents — govern before they act

Orivael sits between your users, your agents, and your tools and enforces policy on every action before it runs. It blocks unsafe or irreversible tool calls, routes high-risk actions to human approval, and signs every decision into a tamper-evident audit trail. Built for teams shipping AI agents that can't afford a "the bot deleted prod" incident. • Intercepts tool calls, not just text • PASS / WARN / BLOCK + approval • Signed audit log • Self-hostable, microsecond hot path