LangSmith

Trace, test and monitor LLM apps in production.

TypeScript Proprietaryupdated 1 week ago

README.md

LangSmith is a platform to trace, evaluate and monitor LLM applications — capture every step of a run, build eval datasets, and watch quality in production.

Continue your stack

What teams reach for next — and why each earns a place beside LangSmith. Ranked by curator confidence.

Pairs well with

LangGraph

Build stateful, multi-actor LLM apps as graphs — durable execution, human-in-the-loop, streaming.

Why it fitsOnce your graph runs in production you'll want to see why a run failed — LangSmith traces every node.

deepagents

LangChain's batteries-included agent harness on LangGraph — planning, sub-agents with isolated context, filesystem, shell, skills, human-in-the-loop and persistent memory out of the box.

Why it fitsThe README's own production pairing: LangSmith supplies tracing, evaluation and monitoring for deepagents deployments.

Alternative to See all + compare →

future-agi

Self-hostable platform for the whole agent-quality loop: tracing, evals, simulations, datasets, guardrails and an LLM gateway — one feedback loop from prototype to production. Apache 2.0.

Why it fitsSame job — trace, test and monitor LLM apps. LangSmith is the polished hosted incumbent tied to the LangChain orbit; Future AGI is the Apache-2.0 self-hostable that adds simulation and guardrails.