{"data":{"slug":"meta-llama-purplellama","name":"PurpleLlama","tagline":"Set of tools to assess and improve LLM security","github_url":"https://github.com/meta-llama/PurpleLlama","owner":"meta-llama","repo":"PurpleLlama","owner_avatar_url":"https://avatars.githubusercontent.com/u/153379578?v=4","primary_language":"Python","stars":4330,"forks":766,"topics":[],"archived":false,"github_pushed_at":"2026-07-27T21:53:59+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/meta-llama-purplellama","markdown_url":"https://www.graphcanon.com/tools/meta-llama-purplellama.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/meta-llama-purplellama","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=meta-llama-purplellama","description":"Set of tools to assess and improve LLM security.","homepage_url":null,"license":"Other","open_issues":80,"watchers":67,"ai_summary":"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.","readme_excerpt":"## License\n\nComponents within the Purple Llama project will be licensed permissively enabling both research and commercial usage.\nWe 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.\nMore concretely evals and benchmarks are licensed under the MIT license while any models use the corresponding Llama Community license. See the table below:\n\n| **Component Type** |            **Components**            |                                          **License**                                           |\n| :----------------- | :----------------------------------: | :--------------------------------------------------------------------------------------------: |\n| Evals/Benchmarks   | Cyber Security Eval (others to come) |                                              MIT                                               |\n| Safeguard             |             Llama Guard              | [Llama 2 Community License](https://github.com/facebookresearch/PurpleLlama/blob/main/LICENSE) |\n| Safeguard             |             Llama Guard 2            | [Llama 3 Community License](https://github.com/meta-llama/llama3/blob/main/LICENSE) |\n| Safeguard             |             Llama Guard 3-8B            | [Llama 3.2 Community License](LICENSE) |\n| Safeguard             |             Llama Guard 3-1B            | [Llama 3.2 Community License](LICENSE) |\n| Safeguard             |             Llama Guard 3-11B-vision            | [Llama 3.2 Community License](LICENSE) |\n| Safeguard             |             Prompt Guard            | [Llama 3.2 Community License](LICENSE) |\n| Safeguard          |             Code Shield              | MIT |\n\n---\n\n## Getting Started\n\nAs part of the [Llama reference system](https://github.com/meta-llama/llama-agentic-system), we’re integrating a safety layer to facilitate adoption and deployment of these safeguards.\nResources to get started with the safeguards are available in the [Llama-recipe GitHub repository](https://github.com/meta-llama/llama-recipes).","github_created_at":"2023-12-06T21:29:41+00:00","created_at":"2026-07-11T23:42:21.681554+00:00","updated_at":"2026-08-05T06:01:03.54359+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"benchmarks","name":"benchmarks"},{"slug":"evaluations","name":"evaluations"},{"slug":"llm-security-tools","name":"llm security tools"},{"slug":"security","name":"security"}],"trust":{"provenance":{"is_fork":false,"github_id":728399986,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-05T06:01:02.500Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":0,"days_since_push":8,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T23:42:29.830Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-05T06:01:03.206Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-05T06:01:03.206Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-05T06:01:03.206Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need permissive licenses that fit both research and commercial purposes","For integrating safety layers in LLM deployments with community-supported safeguards"],"when_not_to_use":["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"],"source":"enrich:decision_facts","observed_at":"2026-07-17T03:08:28.164Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"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."}]}}