hermes-labs-ai/hermes-jailbench
Zero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench
GitHub repository with 6 stars and 2 forks.
Language: Python
Topics: ai-red-team, ai-reliability, ai-safety, benchmark, claude-code-plugin, deterministic-testing, gemini-cli-extension, github-actions, hermes-labs, jailbreak