The Eval Index / Red Teaming & Safety / #129

matheusht/redthread

by matheusht · Red Teaming & Safety · updated 10d ago

An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision evaluations, and synthesizing validated guardrails for safe self-improvement.

54
momentum
33
stars
3
forks
#129
rank
View on GitHub →