{"id":"openai-guardrails","name":"OpenAI Guardrails","maker":"OpenAI","url":"https://openai.github.io/openai-guardrails-python/","repo":"openai/openai-guardrails-python","package":"pypi:openai-guardrails","summary":"Libraries for Python and TypeScript that wrap OpenAI client calls with configurable safety checks.","details":"Adds checks such as personal data detection, jailbreak and prompt injection detection, and moderation to model calls, configured through a JSON file or a visual tool. The libraries are MIT licensed.","open_source":true,"hosted":false,"speaks":["openai-api"],"verified":"2026-11-15","category":"safety","category_name":"Guardrails and security","page":"https://modelmoot.com/tools/openai-guardrails","reviewed":"2026-11-15","checked":{"at":"2026-11-15T15:07:43.409Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}