Pinned Loading

1. llm-safety-evaluation-lab llm-safety-evaluation-lab Public

   OWASP-inspired LLM red teaming framework with adversarial test cases, automated benchmarking, and cross-model safety evaluation.

   Python 1

2. pw-cli pw-cli Public

   Modern CLI password generator with memorable passphrases and an encrypted local vault.

   Python 2

3. rusafetybench rusafetybench Public

   Open adversarial benchmark for Russian-language LLM safety evaluation.

   1

4. multi-agent-safety-sim multi-agent-safety-sim Public

   Experimental Python framework for simulating multi-agent AI safety failure modes

   Python