langsmith-sdk vs openllmetry
LLM tracing and observability projects compared
langsmith-sdk sends Python and JavaScript/TypeScript application traces to the LangSmith platform for debugging, evaluation, and monitoring. openllmetry instruments Python LLM applications with OpenTelemetry, so teams can export telemetry to an existing compatible observability system.

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.

openllmetry: Observe LLM Applications with OpenTelemetry
OpenLLMetry adds OpenTelemetry-based tracing and metrics for LLM applications, providers, frameworks, and vector databases. It suits teams that want AI-specific observability in their existing telemetry stack rather than a separate monitoring format.
| langsmith-sdk | openllmetry | |
|---|---|---|
| Language | Python | Python |
| License | MIT | Apache-2.0 |
| Stars | 1.1k | 7.5k |
| Forks | 315 | 1.1k |
| Last analyzed | Oct 28, 2026 | Oct 3, 2026 |
Key differences
- langsmith-sdk provides Python and JavaScript/TypeScript clients, while openllmetry is a Python project.
- langsmith-sdk sends traces to the LangSmith platform; openllmetry exports standard OpenTelemetry data to supported destinations such as Datadog, Grafana, Honeycomb, and the OpenTelemetry Collector.
- openllmetry covers instrumentation for LLM providers, frameworks, vector databases, and other application components; langsmith-sdk focuses on tracing application runs and wrapping OpenAI clients.
- langsmith-sdk is licensed under MIT, while openllmetry is licensed under Apache-2.0.
- The listed repository figures are 1.1k stars and 307 forks for langsmith-sdk, and 7.5k stars and 1.1k forks for openllmetry.
Choose langsmith-sdk if you…
- need Python or JavaScript/TypeScript clients for tracing an existing LLM application to LangSmith.
- want LangSmith workflows for debugging, evaluation, or monitoring, including with LangChain or an OpenAI client.
- prefer a focused client SDK and can use the LangSmith platform and an API key.
Choose openllmetry if you…
- want LLM telemetry in an existing OpenTelemetry-compatible observability stack.
- need Python instrumentation for providers, frameworks, or vector databases alongside other application telemetry.
- prefer a convenience SDK or individual instrumentations that fit an existing OpenTelemetry setup.
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.