Trial Guardrail Defense
PurpleLlama (Llama Guard, Prompt Guard, LlamaFirewall)
PurpleLlama is Meta's open umbrella project providing LLM safeguard models (Llama Guard for input/output content moderation, Prompt Guard for prompt injection and jailbreak detection, Code Shield for inference-time insecure-code filtering) plus cyber-risk evals (CyberSec Eval 1-3). Aimed at developers building LLM applications.
Worth piloting on a real project; expect some rough edges.
Facts
- Repository
- meta-llama/PurpleLlama
- Homepage
- github.com
- Listed via
- Curated
- First seen
- 2026-11-08
- License
- open source
- Stars
- 4,478
- Last commit
- 2026-11-09
- Checked
- 2026-11-13
Techniques
Listing is not endorsement. Summaries and notes are AI-assisted and reviewed; repository facts refresh automatically.