Home/LLM Frameworks/PurpleLlama
PurpleLlama logo

PurpleLlama

Enrichment pending
meta-llama/PurpleLlama

Set of tools to assess and improve LLM security.

GraphCanon updated today · GitHub synced today

4.3k
Stars
747
Forks
75
Open issues
67
Watchers
1w
Last push
Python OtherCreated Dec 6, 2023

Trust & integrity

Full report
Maintenance
Active (10d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Organization account
As of today · Source: github_public_v1
Security (OSV)
No lockfile
As of today · Source: none

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

Set of tools to assess and improve LLM security.

Capability facts

Languages
python

Source: github.language · Jul 11, 2026

Categories

Tags

README

License

Components within the Purple Llama project will be licensed permissively enabling both research and commercial usage. We believe this is a major step towards enabling community collaboration and standardizing the development and usage of trust and safety tools for generative AI development. More concretely evals and benchmarks are licensed under the MIT license while any models use the corresponding Llama Community license. See the table below:

Component TypeComponentsLicense
Evals/BenchmarksCyber Security Eval (others to come)MIT
SafeguardLlama GuardLlama 2 Community License
SafeguardLlama Guard 2Llama 3 Community License
SafeguardLlama Guard 3-8BLlama 3.2 Community License
SafeguardLlama Guard 3-1BLlama 3.2 Community License
SafeguardLlama Guard 3-11B-visionLlama 3.2 Community License
SafeguardPrompt GuardLlama 3.2 Community License
SafeguardCode ShieldMIT

Getting Started

As part of the Llama reference system, we’re integrating a safety layer to facilitate adoption and deployment of these safeguards. Resources to get started with the safeguards are available in the Llama-recipe GitHub repository.