Braintrust

Braintrust

Hosted platform for tracing AI apps and agents, scoring them with experiments, and monitoring quality in production.

Proprietary (open source SDKs)PythonTypeScriptGoJavaRubyC#v0.45.0

What it supports

  • Evaluates multi-step agents and tool calls: supportedEvaluates multi-step agents and tool callsDocs
  • LLM as a judge scoring: supportedLLM as a judge scoringDocs
  • Tracing: supportedTracingDocs
  • Runs in CI: supportedRuns in CIDocs

Install

pip install braintrust

Links

Official documentationgithub.com/braintrustdata/braintrust-sdk-pythonHosted option: BraintrustPricing

Other eval frameworks

Inspect AIpromptfooDeepEvalPydantic EvalsHarborLangfuseOpikMLflow GenAI EvaluationArize PhoenixW&B WeaveRagasGoogle ADK EvaluationLangSmith EvaluationMicrosoft Foundry EvaluationsGen AI Evaluation Service

Get the weekly agent stack update

New official MCP servers, spec changes and harness releases, checked against the source. One email a week, no fluff.

Reviewed Oct 9, 2026.