Llama Guard / Purple Llama
Set of tools to assess and improve LLM security.
Llama Guard / Purple Llama scores 6/10 (Solid) in Guardrails & Security.
Language Python License Custom (see repo) Stars 4.3k★ Type heavyweight Self-host Yes Repo meta-llama/PurpleLlama Homepage https://ai.meta.com/llama/purple-llama/
Quality
Solid 6.0
Adoption 41
Activity 57
Maturity 94
Community 48
Capability 50
Show the math
Overall 6/10
value = 6/10
score = value
Adoption 4.7/10
value = 40.7/100
score = 1 + 9 * value / 100
Activity 6.1/10
value = 56.5/100
score = 1 + 9 * value / 100
Maturity 9.5/10
value = 94/100
score = 1 + 9 * value / 100
Community 5.3/10
value = 47.7/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
4.3k★ GitHub stars
28/90d Recent commits
9 devs/90d Recent contributors
2.6y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- No license
No OSS license
No recognized open-source license is declared; using it commercially is legally ambiguous.
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
- Heavyweight
Heavyweight
Resource-heavy to run (GPU, large memory, or multi-service stack).
llama-guard prompt-guard llamafirewall moderation meta