langchain-ai/langsmith-sdk

LangSmith Client SDK Implementations

What it solves

It provides a way for teams to debug, evaluate, and monitor language models and intelligent agents. It addresses the difficulty of seeing exactly what is happening inside complex LLM applications to ensure they are performing correctly.

How it works

The SDKs allow developers to integrate LangSmith into their applications. By using wrappers or decorators (like @traceable), the SDK captures and sends execution traces of LLM calls and agent logic to the LangSmith platform for analysis.

Who it’s for

Developers building LLM-powered applications and intelligent agents who need visibility into their model's performance and behavior.

Highlights

  • Native integration with LangChain Python and JS libraries.
  • Supports both Python and JavaScript/TypeScript environments.
  • Ability to wrap existing LLM clients (e.g., OpenAI) to automatically trace calls.

Related

  • Project
    langfuse/langfuse-python

    A Python SDK for the Langfuse platform that provides observability, tracing, prompt management, and evaluation tools for LLM applications.

  • Project
    langwatch/langwatch

    LangWatch is an open‑core platform for LLM observability, testing, routing, and governance. It lets teams trace every LLM call, run simulation tests, manage prompts, enforce budgeted virtual keys, and get usage reports across coding assistants, LangChain‑style agents, and major model providers.

  • Project
    JudgmentLabs/judgeval

    An open-source Python SDK for agent improvement that provides tracing and agent-judge evaluation to detect failures and validate fixes for LLM-powered applications.

  • Project
    lmstudio-ai/lmstudio-js

    The official TypeScript/JavaScript SDK for LM Studio, enabling developers to integrate local LLMs into applications with advanced model management and agentic capabilities.

  • Project
    traceloop/openllmetry

    An open-source observability framework built on OpenTelemetry that provides complete tracing and monitoring for LLM applications, providers, and vector databases.