Skip to content
View romanlutz's full-sized avatar

Highlights

  • Pro

Organizations

@fairlearn

Block or report romanlutz

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Starred repositories

Showing results

Public CVE list maintained by Microsoft Security's Frontier Offensive Research & Generative Exploitation (FORGE) Lab.

JavaScript 27 2 Updated Nov 12, 2026

Medusa's Memory Heist Card Game - learn about AI Safety through a video game

HTML 12 3 Updated Aug 4, 2026

Requirement-driven evaluation harness for AI agents and LLM applications. Generate behavior-specific test cases, run them against any target (hosted models, callable wrappers, OTel-traced agents), …

Python 364 50 Updated Nov 16, 2026

Seeing if Fable 5 can one-shot this game

HTML 18 1 Updated Aug 5, 2026

Converts English text to IPA notation

Python 409 73 Updated Jun 1, 2023

AI model safety scanner built on NVIDIA garak

Ruby 684 116 Updated Nov 12, 2026
Jupyter Notebook 31 8 Updated Oct 22, 2024

Open Machine Learning

PHP 761 130 Updated Nov 3, 2026

Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Me…

TypeScript 431 70 Updated Nov 16, 2026

Collection of evals for Inspect AI

Python 747 487 Updated Nov 16, 2026

Inspect: A framework for large language model evaluations

Python 3,269 939 Updated Nov 16, 2026

Repository for "StrongREJECT for Empty Jailbreaks" paper

Jupyter Notebook 162 9 Updated Nov 3, 2024

Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Python 609 87 Updated Feb 27, 2026

A database migrations tool for SQLAlchemy.

Python 4,481 392 Updated Oct 30, 2026

A pytest-native safety and security testing framework for agentic AI applications

Python 426 61 Updated Nov 12, 2026

Repository for "Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models"

Python 2 Updated Oct 20, 2026

Squad: AI agent teams for any project

TypeScript 3,400 521 Updated Nov 16, 2026

A tool that validates academic paper references

Python 573 65 Updated Oct 27, 2026

Gas Town - multi-agent workspace manager

Go 18,816 1,702 Updated Nov 14, 2026

An extremely fast Python type checker and language server, written in Rust.

Python 20,101 348 Updated Nov 16, 2026

This repository is for active development of the Azure SDK for Python. For consumers of the SDK we recommend visiting our public developer docs at https://learn.microsoft.com/python/azure/ or our v…

Python 5,624 3,420 Updated Nov 16, 2026

Playwright MCP server

TypeScript 39,745 3,448 Updated Nov 16, 2026

[ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments

Python 67 11 Updated Feb 9, 2026

Benchmarking LLM agents on Cyber Threat Investigation.

Jupyter Notebook 164 28 Updated Nov 16, 2026

Simple Prompt Injection Kit for Evaluation and Exploitation

Python 274 58 Updated Nov 10, 2026

Recursively scan a Python module and export numpydoc docstrings to JSON

TypeScript 6 2 Updated May 28, 2026

Open-Source Apprenticeship Program

3 Updated May 22, 2025

Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Python 142 15 Updated Dec 2, 2024
Python 12 3 Updated Jun 16, 2026

File support for asyncio

Python 3,274 187 Updated Oct 25, 2026
Next