{"id":"guardrails-ai","name":"Guardrails AI","maker":"Guardrails AI","url":"https://guardrailsai.com","repo":"guardrails-ai/guardrails","package":"pypi:guardrails-ai","summary":"A Python framework that checks and constrains LLM inputs and outputs with validators from a shared hub.","details":"Wraps model calls in input and output guards built from validators for risks such as toxicity, personal data and format, and can also produce structured output. It runs as a library or as a local server with an OpenAI-compatible endpoint. Validators are moving to ordinary PyPI packages and the hosted remote inference was discontinued in 2026. The code is open source under Apache 2.0.","open_source":true,"hosted":false,"speaks":["openai-api"],"verified":"2026-11-15","category":"safety","category_name":"Guardrails and security","page":"https://modelmoot.com/tools/guardrails-ai","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true,"repository":{"at":"2026-11-15T23:25:51.807Z","archived":false,"licence":"Apache-2.0","language":"Python","last_change":"2026-11-11T02:11:16.000Z","latest_release":{"tag":"v0.11.0","published":"2026-08-14T14:22:32.000Z"}}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}