GraphCanon updated 2w · GitHub synced 2w · 25 views this month
Decision brief
PurpleLlama provides tools to enhance the security and trust of large language models using MIT licenses for benchmarks and community-specific licenses for safeguard components.
Good fit when
- When you need permissive licenses that fit both research and commercial purposes
- For integrating safety layers in LLM deployments with community-supported safeguards
Avoid when
- If your project requires consistent licensing across all components under one standard license like GPL or Apache-2.0
- When you prefer not to adhere to the Llama Community Licenses for safeguard functionalities
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Active (8d since push)
- As of 2w
- Provenance
- Not a fork · Organization account
- As of 2w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install PurpleLlamaSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
PurpleLlama offers tools for assessing and enhancing the safety and trustworthiness of large language models (LLM). It includes evaluative benchmarks under MIT license and safeguard components under various Llama Community Licenses.
Capability facts
- Languages
- python
Source: github.language · Aug 5, 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 Type | Components | License |
|---|---|---|
| Evals/Benchmarks | Cyber Security Eval (others to come) | MIT |
| Safeguard | Llama Guard | Llama 2 Community License |
| Safeguard | Llama Guard 2 | Llama 3 Community License |
| Safeguard | Llama Guard 3-8B | Llama 3.2 Community License |
| Safeguard | Llama Guard 3-1B | Llama 3.2 Community License |
| Safeguard | Llama Guard 3-11B-vision | Llama 3.2 Community License |
| Safeguard | Prompt Guard | Llama 3.2 Community License |
| Safeguard | Code Shield | MIT |
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.
For agents
This page has a .md twin and JSON over the API.