Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
Plexiglasssafellama.github.ioPlexiglass is a Python-based security toolbox developed by SafeLlama to test vulnerabilities and safeguard Language Learning Models (LLMs). It offers versatile testing modes, including a command-line interface (CLI) and a standalone Python module, and uses litellm to support a range of LLMs. The project emphasizes community involvement and invites contributions to extend its capabilities for securing AI systems.
Parse Score
Sources
egnyte.com shapes more of what AI says about Plexiglass than any other source, at 100% of its citations.
