langsmith-sdk vs weave
LLM tracing and evaluation SDKs compared
langsmith-sdk provides Python and JavaScript/TypeScript clients that send application traces to the LangSmith platform. weave is a Python toolkit that traces calls and supports structured evaluations; its workflow centers on instrumentation in application code and organizing runs across experimentation and production.
langsmith-sdk: Trace and Evaluate LLM Applications with LangSmith
LangSmith SDKs from LangChain let Python and JavaScript/TypeScript applications trace, evaluate, and monitor language models and agents through the LangSmith platform. This repository is archived; the SDKs have moved to separate Python and JavaScript repositories.
weave: Trace and Evaluate Generative AI Applications
Weave helps developers trace language model inputs, outputs, and function calls, then organize and evaluate application runs. It suits teams building AI features that need debugging and repeatable comparisons across experiments and production.
| langsmith-sdk | weave | |
|---|---|---|
| Language | Python | Python |
| License | MIT | Apache-2.0 |
| Stars | 1.1k | 1.1k |
| Forks | 315 | 171 |
| Last analyzed | Oct 28, 2026 | Oct 3, 2026 |
Key differences
- langsmith-sdk supports Python and JavaScript/TypeScript, while weave is described as a Python toolkit requiring Python 3.10 or higher.
- langsmith-sdk sends traces to the LangSmith platform and requires platform access and an API key; weave requires a Weights & Biases account.
- weave describes tracing decorated functions, capturing inputs and outputs, and representing calls as a trace tree; langsmith-sdk focuses on connecting application runs to platform workflows.
- langsmith-sdk integrates with LangChain Python and LangChain JS and can wrap OpenAI clients; weave highlights the `weave.op` decorator and tracking model calls alongside validation and data transformations.
- langsmith-sdk is licensed under MIT, while weave is licensed under Apache-2.0.
- weave's README says work on the Weave engine and boards is paused while the project focuses on tracing and evaluations; langsmith-sdk is described as an SDK repository for LangSmith platform clients.
Choose langsmith-sdk if you…
- need Python and JavaScript/TypeScript clients for tracing an existing application.
- want to send traces to LangSmith for debugging, evaluation, or monitoring.
- use LangChain or want to wrap an OpenAI client to add tracing.
Choose weave if you…
- want Python tracing through decorated functions and trace trees.
- need repeatable evaluations to compare model or prompt changes.
- want to track model calls alongside validation and data transformations across experimentation and production.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.