Download
Purple Llama is an umbrella safety initiative that aggregates tools, benchmarks, and mitigations to help developers build responsibly with open generative AI. Its scope spans input and output safeguards, cybersecurity-focused evaluations, and reference shields that can be inserted at inference time. The project evolves as a hub for safety research artifacts like Llama Guard and Code Shield, along with dataset specs and how-to guides for integrating checks into applications. CyberSecEval, one of its flagship components, provides repeatable evaluations for security risk, including agent-oriented tasks such as automated patching benchmarks. The aim is to make safety practical: ship testable baselines, publish metrics, and provide drop-in implementations that reduce friction for teams adopting Llama. Documentation and sites attached to the repo walk through setup, usage, and the rationale behind each safeguard, encouraging community contributions.
Features
- Input and output safety guards for LLM apps
- Cybersecurity evaluations including agent patching tasks
- Reference “shields” for inference-time mitigation
- Reusable datasets and metrics for safety benchmarking
- Integration patterns for common Llama deployment stacks
- Documentation for policy design and operationalization
Project Samples
