Devtoolwatch BoardGet it every Monday

LangSmith SDK review

LangSmith SDK is the Python and JavaScript client library for tracing, debugging, evaluating, and monitoring LLM applications on the LangSmith platform.

Updated Nov 1, 2026. Review written Oct 22, 2026 from the project's own sources; usage data refreshed every Monday.

TL;DR

LangSmith SDK provides Python and JavaScript/TypeScript clients for the LangSmith observability and evaluation platform. It suits teams building LLM apps and agents who want traces, evaluation, and monitoring. This repository is archived, and the SDKs now live in separate repositories. The packages are unchanged.

LangSmith SDK at a glance

Category
Evals and observability
Maintained by
LangChain (organization, @langchain-ai on GitHub)
License
MIT
Language
Python, TypeScript, JavaScript
Repository
github.com/langchain-ai/langsmith-sdk
Website
docs.smith.langchain.com
npm package
langsmith 0.11.0
PyPI package
langsmith 0.14.12
Latest release
langsmith 0.14.12 on PyPI, Oct 21, 2026
First published
May 30, 2023

What LangSmith SDK does

  • LangSmith SDK traces LLM application calls and sends them to the LangSmith platform for debugging and monitoring.
  • LangSmith SDK wraps OpenAI clients with wrap_openai in Python and wrapOpenAI in JavaScript to trace chat completions.
  • LangSmith SDK provides a traceable decorator or function for instrumenting your own code.
  • LangSmith SDK supports evaluation of language models and agents, including comparative evaluators.
  • LangSmith SDK can send OTLP traces, including to an Agent environment.
  • LangSmith SDK integrates natively with the LangChain Python and LangChain JS libraries, and it works with any LLM application.

How it works

You install the langsmith package from PyPI or npm. Then you set the LANGSMITH_TRACING and LANGSMITH_API_KEY environment variables, plus LANGSMITH_WORKSPACE_ID for org-scoped keys. Next you wrap your LLM client or decorate functions with traceable. Traces go to the LangSmith platform, which can run in the cloud or as a hybrid or self-hosted instance.

How to install and start using LangSmith SDK

With pip

pip install -U langsmith

With pnpm

pnpm add langsmith

Requirements

  • Python 3.10 or later for the Python package
  • A LangSmith account and API key
  • A workspace ID when using org-scoped API keys

First steps

  1. Create a LangSmith account at smith.langchain.com. You can log in with Google, GitHub, or email.
  2. Create an API key under Settings > API Keys > Create API Key, then save it securely.
  3. Set LANGSMITH_TRACING=true and LANGSMITH_API_KEY. Also set LANGSMITH_WORKSPACE_ID if you use an org-scoped key.
  4. Wrap your OpenAI client with wrap_openai or wrapOpenAI, then make a chat completion call to record a trace.

Who LangSmith SDK is for

  • Teams debugging, evaluating, and monitoring LLM applications and agents
  • Developers already using LangChain Python or LangChain JS

Limitations to know

  • LangSmith SDK's repository is archived. New issues and pull requests go to langsmith-python and langsmith-javascript.
  • LangSmith SDK requires the LangSmith platform. You need an account and API key, whether you use cloud, hybrid, or self-hosted.

Is LangSmith SDK growing? Usage data

In the week of Oct 25–31, 2026, LangSmith SDK ranked #251 on the Devtoolwatch Board and #13 in Evals and observability, with a momentum score of 38 out of 100. Its main package had about 32.1M downloads that week, +11% against its own 4-week average.

New GitHub stars per week for LangSmith SDK12 weeks from Aug 9, 2026: 12, 8, 16, 5, 5, 7, 4, 5, 6, 11, 1, 3 new stars, an average of 7 a week.Aug 9week of Oct 25
New GitHub stars per week for the last 12 weeks, from GitHub's stargazer history (today's stargazers by the week they starred).
Show the weekly numbers
New GitHub stars per week for LangSmith SDK
Week ofNew stars
Aug 9, 202612
Aug 16, 20268
Aug 23, 202616
Aug 30, 20265
Sep 6, 20265
Sep 13, 20267
Sep 20, 20264
Sep 27, 20265
Oct 4, 20266
Oct 11, 202611
Oct 18, 20261
Oct 25, 20263

The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.

LangSmith SDK alternatives

Other LLM evals and observability tools on the Board in the week of Oct 25–31, 2026, by momentum:

Evals and observability ranked by momentum, the week of Oct 25–31, 2026
RankToolStarsDownloads/wk
#1SkillSpectorSkillSpector is NVIDIA's security scanner that checks AI agent skills for vulnerabilities, malicious patterns, and supply-chain risks…23.7k–
#2JudgevalJudgeval is an open-source Python SDK for tracing and evaluating LLM-powered agents with prompt-based judges and online monitoring.1.1k80.2k
#3A.I.G (AI-Infra-Guard)A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak…7.2k–
#4LangfuseLangfuse is an open source LLM engineering platform for tracing, evaluating, prompt management, and debugging LLM applications and agents.36.8k9.8M
#5OpikOpik is an open-source platform from Comet for tracing, evaluating, and monitoring LLM applications, RAG systems, and AI agents.23.1k709.1k
#6promptfoopromptfoo is a CLI and library for evaluating and red-teaming LLM-based apps, including prompts, agents, and RAG pipelines.26.7k1.2M

All LLM evals and observability tools, ranked

Recent LangSmith SDK releases

LangSmith SDK FAQ

Is LangSmith SDK free and open source?

Yes. LangSmith SDK's source code is on GitHub (langchain-ai/langsmith-sdk) under the MIT license, so you can use it for free.

How do I install LangSmith SDK?

Run pip install -U langsmith. The install section above has the other options from the project's README.

Is LangSmith SDK still maintained?

No. The langchain-ai/langsmith-sdk repository is archived, so it's read-only.

How popular is LangSmith SDK?

LangSmith SDK has 1.1k GitHub stars as of Nov 1, 2026. It gained 3 new stars in the week of Oct 25–31, 2026, against a 12-week average of 7 a week. Its main package had about 32.1M downloads that week, +11% against its own 4-week average. That made it #13 among LLM evals and observability tools on the Devtoolwatch Board.

What are the best alternatives to LangSmith SDK?

Other LLM evals and observability tools on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: SkillSpector (#1), Judgeval (#2), A.I.G (AI-Infra-Guard) (#3), Langfuse (#4), Opik (#5). The alternatives table above has their numbers.

What is LangSmith SDK?

LangSmith SDK is the set of Python and JavaScript client libraries for the LangSmith observability and evaluation platform. Teams use it to debug, evaluate, and monitor language models and agents.

Where did the LangSmith SDK code move?

The Python SDK moved to langchain-ai/langsmith-python, and the JS SDK moved to langchain-ai/langsmith-javascript. The langsmith packages on PyPI and npm are unchanged.

Does LangSmith SDK only work with LangChain?

No. LangSmith works with any LLM application. It has a native integration with LangChain, and it supports providers and frameworks such as OpenAI, Anthropic, CrewAI, Vercel AI SDK, and Pydantic AI.

Can LangSmith be self-hosted?

Yes. A LangSmith instance can run in the cloud, as a hybrid setup, or self-hosted. All options include observability, evaluation, prompt engineering, and deployment.

Sources

  1. langchain-ai/langsmith-sdk on GitHub
  2. LangSmith SDK README
  3. langsmith on npm
  4. langsmith on PyPI
  5. LangSmith SDK website
  6. Release v0.14.9 (Oct 15, 2026)
  7. Release v0.14.8 (Oct 13, 2026)
  8. Release v0.14.7 (Oct 9, 2026)
  9. Devtoolwatch Board, the week of Oct 25–31, 2026

LangSmith SDK README badge

Maintainers can show the tool's weekly Board rank in their README:

Devtoolwatch badge for LangSmith SDK

[![Devtoolwatch](https://index.devtoolwatch.com/badge/langsmith.svg)](https://index.devtoolwatch.com/tools/langsmith/)

How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].