Skip to main content

​
Autoevals

Pre-built scoring functions for evaluating LLM outputs, including factuality, similarity, and answer relevance scorers. Use it alongside the main SDK to score evaluations without writing your own scorers from scratch. API reference · pip: autoevals

​
LangChain

Braintrust’s LangChain Python integration, which adds Braintrust tracing to LangChain workflows. The braintrust-langchain package is deprecated — the integration is now included in the main braintrust package (pip install braintrust). API reference

​
Google ADK

Braintrust’s integration for Google’s Agent Development Kit (ADK). The braintrust-adk package is deprecated — the integration is now included in the main braintrust package (pip install braintrust). API reference