meta-llama/PurpleLlama
Set of tools to assess and improve LLM security.
The Security Toolkit for LLM Interactions
Set of tools to assess and improve LLM security.
Adding guardrails to large language models.
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
The platform for LLM evaluations and AI agent testing
DeepTeam is a framework to red team LLMs and LLM systems.
1 capture since 2026-05-25