· Observability & evals/ How you run it

LangSmith

LangSmith is a observability & evals option for building AI agents. Tracing, datasets and evals from the LangChain team.

Proprietary · freemium · hosted service only · SDKs for Python and TypeScript · by LangChain · verified 2026-08-21

Official docsAdd to a stackAll observability & evals options
· When to reach for it/ Fit
  • You are choosing a observability & evals component — how you run it.
  • You are happy to depend on a hosted service and would rather not operate this yourself.
· What it takes to run/ Setup
Environment
LANGSMITH_API_KEY=
· LangSmith vs the alternatives/ 5 others
OptionWhat it doesLicenceSelf-host
LangSmithTracing, datasets and evals from the LangChain team.ProprietaryNo
LangfuseOpen-source tracing, prompt management and evals. Self-hostable in one compose file.Open sourceYes
BraintrustEval-first platform — scorers, datasets and a playground for prompt iteration.ProprietaryYes
Arize PhoenixOpenTelemetry-native tracing and evals you can run locally.Open sourceYes
Pydantic LogfireOpenTelemetry observability with first-class Python and Pydantic AI support.Open sourceNo
promptfooLocal eval and red-team harness that runs in CI. No account needed.Open sourceYes
· For agents/ This page, machine-readable

Every page here answers to Accept: text/markdown and returns the same content at roughly a tenth the tokens. No separate site, no toggle — same URL.

curl -s -H "Accept: text/markdown" https://newagent.build/c/langsmith