{"id":"braintrust","name":"Braintrust","maker":"Braintrust","url":"https://www.braintrust.dev","docs":"https://www.braintrust.dev/docs","package":"pypi:braintrust","summary":"A hosted platform for running evaluations, logging traces and managing prompts for AI applications.","details":"Offers an evaluation framework, tracing, datasets, a prompt playground and online scoring, reached through SDKs for Python and TypeScript and a web interface. It also provides an AI proxy that routes calls to several model providers. The platform needs an account; the SDKs are public but the service itself is closed.","open_source":false,"hosted":true,"speaks":["opentelemetry"],"also":["gateways"],"verified":"2026-11-15","category":"observability","category_name":"Observability and evaluation","page":"https://modelmoot.com/tools/braintrust","reviewed":"2026-11-15","checked":{"at":"2026-11-15T13:03:28.711Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}