---
title: "Judgeval SDK Reference"
description: "Reference documentation for the Judgeval SDK"
sidebar:
  label: "SDK Overview"
  icon: "code"
seo:
  title: "Judgeval SDK Reference | Python and TypeScript APIs for Judgment"
  description: "Reference for the Judgeval SDK APIs used to send traces, run evaluations, manage datasets, and work with judges in Judgment."
---

The Judgeval SDK provides a complete toolkit for evaluating, monitoring, and optimizing AI agents. Trace agent execution in production, run evaluations with custom scoring rubrics, manage test datasets, and version prompts with integrated evaluation workflows.

## Core SDK Components

**Python**

**[Judgeval](/sdk-reference/python/judgeval)**

Primary client for evaluation, datasets, and prompt management

**[JQL](/sdk-reference/python/jql)**

Build and execute structured queries over traces, spans, and sessions

**[Tracer](/sdk-reference/python/trace/tracer)**

Capture and monitor agent execution traces for debugging and analysis

**[Dataset](/sdk-reference/python/datasets/dataset/Dataset)**

Manage collections of examples for batch evaluation

**[Judge](/sdk-reference/python/judges)**

Create custom local scorers with typed responses

**[Prompt](/sdk-reference/python/prompts/prompt)**

Version and manage prompts with integrated evaluation

**TypeScript**

**[Judgeval](/sdk-reference/typescript/judgeval)**

The main client for running evaluations and managing projects

**[JQL](/sdk-reference/typescript/jql)**

Build and execute structured queries over traces, spans, and sessions

**[Tracer](/sdk-reference/typescript/trace/tracer)**

Capture and monitor agent execution traces for debugging and analysis

**[JudgmentTracerProvider](/sdk-reference/typescript/trace/judgment-tracer-provider)**

Global singleton managing tracer registration and context propagation