# LangSmith SDK review

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

Devtoolwatch Board, the week of Oct 25–31, 2026. Canonical page: https://index.devtoolwatch.com/tools/langsmith/

## 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](https://index.devtoolwatch.com/categories/evals-and-observability/)
- **Maintained by:** LangChain (organization, [@langchain-ai](https://github.com/langchain-ai) on GitHub)
- **License:** MIT
- **Language:** Python, TypeScript, JavaScript
- **Repository:** [github.com/langchain-ai/langsmith-sdk](https://github.com/langchain-ai/langsmith-sdk)
- **Website:** [docs.smith.langchain.com](https://docs.smith.langchain.com/)
- **npm package:** [langsmith](https://www.npmjs.com/package/langsmith) 0.11.0
- **PyPI package:** [langsmith](https://pypi.org/project/langsmith/) 0.14.12
- **Latest release:** [langsmith 0.14.12](https://pypi.org/project/langsmith/) 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 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

- 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.

## Usage data (the week of Oct 25–31, 2026)

- Board rank: #251 overall, #13 in Evals and observability, momentum score 38
- Downloads that week: 32.1M (+11% vs 4-week average)
- New GitHub stars per week (last 12 weeks): Aug 9: 12; Aug 16: 8; Aug 23: 16; Aug 30: 5; Sep 6: 5; Sep 13: 7; Sep 20: 4; Sep 27: 5; Oct 4: 6; Oct 11: 11; Oct 18: 1; Oct 25: 3

## LangSmith SDK alternatives

| Rank | Tool | Stars | Downloads/wk |
|---|---|---|---|
| #1 | [SkillSpector](https://index.devtoolwatch.com/tools/nvidia-skillspector/) | 23.7k | – |
| #2 | [Judgeval](https://index.devtoolwatch.com/tools/judgmentlabs-judgeval/) | 1.1k | 80.2k |
| #3 | [A.I.G (AI-Infra-Guard)](https://index.devtoolwatch.com/tools/tencent-ai-infra-guard/) | 7.2k | – |
| #4 | [Langfuse](https://index.devtoolwatch.com/tools/langfuse/) | 36.8k | 9.8M |
| #5 | [Opik](https://index.devtoolwatch.com/tools/opik/) | 23.1k | 709.1k |
| #6 | [promptfoo](https://index.devtoolwatch.com/tools/promptfoo/) | 26.7k | 1.2M |

## 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](https://github.com/langchain-ai/langsmith-sdk)
2. [LangSmith SDK README](https://github.com/langchain-ai/langsmith-sdk/blob/main/README.md)
3. [langsmith on npm](https://www.npmjs.com/package/langsmith)
4. [langsmith on PyPI](https://pypi.org/project/langsmith/)
5. [LangSmith SDK website](https://docs.smith.langchain.com/)
6. [Release v0.14.9 (Oct 15, 2026)](https://github.com/langchain-ai/langsmith-sdk/releases/tag/v0.14.9)
7. [Release v0.14.8 (Oct 13, 2026)](https://github.com/langchain-ai/langsmith-sdk/releases/tag/v0.14.8)
8. [Release v0.14.7 (Oct 9, 2026)](https://github.com/langchain-ai/langsmith-sdk/releases/tag/v0.14.7)
9. [Devtoolwatch Board, the week of Oct 25–31, 2026](https://index.devtoolwatch.com/)