Skip to content
@fabraix

Fabraix

Adversarial verification for AI training and inference

Popular repositories Loading

  1. playground playground Public

    A live environment to stress-test AI agent defenses through adversarial play 🧠

    TypeScript 75 12

  2. nyx nyx Public

    Fully-autonomous AI agent to systematically probe AI systems for security vulnerabilities 🔍

    TypeScript 9

  3. sync sync Public archive

    GitHub Action to sync a directory to another repository via SSH 🔄

    Shell 3

  4. CrabTrap CrabTrap Public

    Forked from brexhq/CrabTrap

    An LLM-as-a-judge HTTP proxy to secure agents in production

    Go

Repositories

Showing 4 of 4 repositories
  • playground Public

    A live environment to stress-test AI agent defenses through adversarial play 🧠

    fabraix/playground's past year of commit activity
    TypeScript 75 MIT 12 5 4 Updated Aug 28, 2026
  • nyx Public

    Fully-autonomous AI agent to systematically probe AI systems for security vulnerabilities 🔍

    fabraix/nyx's past year of commit activity
    TypeScript 9 Apache-2.0 0 0 0 Updated Aug 18, 2026
  • CrabTrap Public Forked from brexhq/CrabTrap

    An LLM-as-a-judge HTTP proxy to secure agents in production

    fabraix/CrabTrap's past year of commit activity
    Go 0 MIT 65 0 0 Updated Jun 28, 2026
  • sync Public archive

    GitHub Action to sync a directory to another repository via SSH 🔄

    fabraix/sync's past year of commit activity
    Shell 3 MIT 0 0 0 Updated Jan 9, 2026

Most used topics

ai-agents ai-security