langsmith
Client library to connect to the LangSmith Observability and Evaluation Platform.
Decision gist · record as of 2026-08-14
Yes. LangSmith is actively maintained, has low install friction, carries no known vulnerabilities, and uses a permissive MIT license. Install it if you build LLM applications and need centralized tracing, debugging, and evaluation—especially if you already use LangChain. The sandbox and mount features add value for teams running secure, data-intensive workloads.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python >= 3.10.
- You must have a LangSmith account and API key to send traces to the platform.
- Low install friction with a pure-Python wheel and 14 runtime dependencies.
License · maintenance · safety
MIT (permissive) — MIT license is permissive; you can use, modify, and distribute this package freely in commercial and private projects with minimal restrictions.
last release 2026-08-11 (3 days) · last repo commit 2026-08-13 · 1,018 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 116,925,137 downloads/mo, #308 on PyPI
Alternatives
Verify before relying
pip install langsmith
import os
os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = "ls_..."
from langsmith import traceable
@traceable
def my_function(input_str: str):
return f"Processed: {input_str}"
my_function("hello")- Whether the package works offline or requires continuous connectivity to the LangSmith platform.
- Performance overhead of tracing on latency-sensitive applications.
- Detailed sandbox feature support and limitations (AWS, GCP, Git mounts).
What it is and what it does
LangSmith is a client library that connects your Python LLM applications to the LangSmith platform for observability, tracing, and evaluation. It provides decorators and wrappers to automatically capture execution traces from language model calls, function executions, and agent workflows, sending them to a centralized dashboard for inspection, debugging, and performance analysis.
The package integrates with popular LLM frameworks like LangChain and supports direct instrumentation via the @traceable decorator. It also includes sandbox utilities for secure execution of code with managed AWS and GCP authentication, and filesystem mounts for S3, GCS, and Git repositories. Core dependencies include httpx and requests for API communication, pydantic for data validation, and websockets for real-time features.
Use it for
- Trace LLM application calls during development to debug agent behavior and model interactions.
- Log production traces to evaluate model performance and collect data for continuous improvement.
- Run benchmark evaluations on collected traces to compare model versions or prompt variations.
- Execute sandboxed code with secure AWS or GCP credentials without storing long-lived keys.
- Mount external data sources (S3, GCS, Git repos) into sandboxes for data-driven evaluations.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
LangSmith is actively maintained, has low install friction, carries no known vulnerabilities, and uses a permissive MIT license. Install it if you build LLM applications and need centralized tracing, debugging, and evaluation—especially if you already use LangChain. The sandbox and mount features add value for teams running secure, data-intensive workloads.
Install
langsmith on PyPI
Before you install
Low install friction with a pure-Python wheel and 14 runtime dependencies. Actively maintained with a recent release (3 days old) and a healthy repository (1018 stars, last commit 2026-08-13).
Requires Python >= 3.10. You must have a LangSmith account and API key to send traces to the platform.
License in practice
MIT license is permissive; you can use, modify, and distribute this package freely in commercial and private projects with minimal restrictions.
Quickstart
pip install langsmith
import os
os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = "ls_..."
from langsmith import traceable
@traceable
def my_function(input_str: str):
return f"Processed: {input_str}"
my_function("hello")Verify before relying
- Whether the package works offline or requires continuous connectivity to the LangSmith platform.
- Performance overhead of tracing on latency-sensitive applications.
- Detailed sandbox feature support and limitations (AWS, GCP, Git mounts).
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 14 packagesanyiodistrohttpxorjsonpackagingpydanticrequests-toolbeltrequestssniffiotyping-extensionsuuid-utilswebsocketsxxhashzstandard |
| Maintenance | Actively maintained 3 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 116,925,137 / month, #308 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: langsmith-0.10.18-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “language model evaluation platform”
- langsmithLangSmith is a Python client SDK for the LangSmith observability and…
- langchainplus-sdkClient library for connecting to LangSmith, a platform for tracing,…
- nvidia-lm-evalEvaluates language models against standardized benchmarks (MMLU,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also langchainplus-sdk · langsmith-mcp-server · langsmith-fetch · traceloop-sdk · langchain-core · langchain-community · opik · langchain-cli · opentelemetry-instrumentation-langchain