About
Antonioni Nascimento started building software at 14, creating games that sparked a lasting passion for numbers, logic, and mathematics. He won a mathematics olympiad and was accepted to the Federal University of Bahia, but chose to follow his own path and stay focused on software development.
In 2019, he co-founded LYS, a software and media development company. During this period, he established strategic partnerships with companies such as Genial Investimentos and Bybit, later selling his stake to begin building KRX.
He also had a brief engagement with a marketing agency but closed that chapter to focus entirely on technology.
Over the years, he accumulated hands-on experience across multiple technology, software, and media cases. He deepened his expertise through courses and mentorships with specialists who built part of their careers in Silicon Valley, and completed programs including the Advanced Cybersecurity Program at Stanford University.
Beyond operations, he maintains the blog at antonioni.dev, publishing technical analysis on technology, venture capital, B2C businesses, and cybersecurity, examining how software, data, and security connect to the construction of scalable products, markets, and companies.
Today, he focuses on KRX, solving advanced software problems at the intersection of cybersecurity, data, and artificial intelligence. In parallel, he invests in D2C companies, supporting founders with technology infrastructure, backoffice, and growth strategy, not operating the businesses directly but providing the technical foundations for scale.
KRX
KRX is a software company focused on solving advanced problems across cybersecurity, data infrastructure, and artificial intelligence.
Investments
I invest in D2C companies, providing technology and backoffice infrastructure to support scale. I do not work directly in operations. My contribution comes through growth consulting, helping founders build the technical and operational foundations that allow their businesses to scale efficiently.
Open Source Projects
Hugo RL-LLM
Production-grade foundation platform for LLM-enhanced Reinforcement Learning with reproducibility, checkpointing, benchmarking, LLM frozen mode, and a plugin system.
Strike
AI-augmented security testing framework in Rust: agent-based vulns discovery/validation, checkpointed workflow engine, LLM routing, CI policy gates (SARIF 2.1.0), and orchestration of nmap/nuclei/sqlmap/etc.
Trace
Hybrid autonomous SWE-Bench agent that reduces context overflow and file retrieval failures using AST-aware search and iterative refinement.
Adversaria
Rust-based adversarial testing harness for LLMs with multi-provider support and structured risk scoring.
Aegis
Deterministic capability firewall for LLMs using taint tracking and policy DSL enforcement instead of prompt filtering.
Zenta
Multi-language CLI and SDK suite for scanning and migrating classical crypto to NIST post-quantum algorithms in ML infrastructure.
ETH.id
Zero-knowledge document verification system combining local privacy filters with LLM semantic verification.
GrabKit
High-quality, resilient web content extraction toolkit that converts messy pages into clean, main-content outputs for AI systems using domain templates, layered heuristics, a proven parser, and optional browser rendering.
Research
At antonioni.dev/blog, I write about technology, venture capital, B2C, and cybersecurity, with a focus on how software, data, and security shape products, markets, and companies in the age of artificial intelligence.