LangSmith

Name: LangSmith
Author: LangChain, Inc.

by LangChain, Inc. · Platform · also known as smith.langchain.com, LangSmith Deployment, LangGraph Platform (former name of the deployment product)

LangChain's hosted platform for tracing, evaluating and deploying LLM applications and agents, with prompt tooling, an LLM gateway and cloud, hybrid or self-hosted options

ProprietaryFreemiumPaidEnterpriseCloudSelf-hostedSelf-hostable

Visit official site Compare

Link verified Nov 2, 2026

Overview

LangSmith is the commercial platform from LangChain, Inc. for operating LLM applications. Its observability layer records traces of what agents did, groups them into threads, supports dashboards, alerts and feedback collection, and builds datasets from production runs. Evaluation covers offline experiments and online evaluators, annotation queues and automation rules, and the Prompt Hub and Playground handle prompt engineering. Newer components include Deployment (hosting LangGraph agents with scheduling, MCP exposure and an Assistants API; formerly LangGraph Platform), Engine (automated detection and diagnosis of recurring trace problems), Fleet (no-code agents), Sandboxes for agent-generated code and an LLM Gateway with cost controls and redaction that traces calls without SDK changes.

Tracing works with LangChain and LangGraph through environment variables but is not limited to them; OpenAI, Anthropic, CrewAI, Vercel AI SDK and Pydantic AI integrations are documented. Plans are Developer (free, single seat), Plus and Enterprise; cloud hosting is in US or EU regions, with hybrid (SaaS control plane, self-hosted data plane) and fully self-hosted deployments reserved for Enterprise. The platform is proprietary, so teams that need a free self-hosted tracing store usually compare it with Langfuse.

Capabilities

Tracing with threads, dashboards, alerts and feedback
Offline and online evaluation, annotation queues and automation rules
Prompt Hub and Playground
Deployment of LangGraph agents with cron, MCP and Assistants API
Engine for automated trace-issue diagnosis
LLM Gateway with cost controls, fallbacks and PII redaction
Cloud (US/EU), hybrid and self-hosted deployment on Enterprise

Typical workflows

Trace a LangGraph agent during development with one environment variable
Turn production failures into an evaluation dataset
Deploy an agent as a managed endpoint with scheduled runs

Strengths

Tightest integration with LangChain and LangGraph
Observability, evals, prompts and deployment in one product
Free Developer tier

Limitations

Proprietary; self-hosting only on Enterprise
Usage metered by traces and platform units
Product renames (LangGraph Platform to LangSmith Deployment) date older docs

Prerequisites

LangSmith account and API key
Application instrumented via LangChain, an SDK or the gateway

Who it is for

Teams building on LangChain and LangGraph
Organizations wanting a managed agent-hosting and observability stack

Alternatives & comparison

Braintrust
Hosted observability and evaluation platform for AI agents with tracing, experiments, pattern detection, a CLI, MCP access and an AI assistant (Loop) that analyzes traces and builds evals
MixedFreemium
Langfuse
Open-source LLM observability and evaluation platform: tracing, LLM-as-judge and human evals, prompt management, datasets and cost dashboards, self-hostable or as Langfuse Cloud
Open sourceOpen source
promptfoo
Open-source, local-first CLI and library for evaluating prompts, models, RAG pipelines and agents, with automated red teaming and CI integration
MixedOpen source
Ragas
Open-source Python library for evaluating LLM and RAG applications with LLM-driven and custom metrics, experiments, dataset management and result tracking
Open sourceOpen source
Weights & Biases
ML experiment tracking, sweeps, artifacts and model registry plus Weave for LLM tracing and evaluation, now sold by CoreWeave within its Forge platform with a free academic tier
MixedFreemium

Compare LangSmith with its alternatives →

Sources & verification

Primary sources consulted for this record. Claims are tied to the fields each source supports; the automated link checker re-verifies every URL on a schedule.

Official documentation
LangSmith documentation
https://docs.langchain.com/langsmith/observability
Supports: capabilities, integrations, deployment_models
checked Nov 1, 2026
Official site
LangSmith Observability
https://www.langchain.com/langsmith/observability
Supports: name, summary
checked Nov 1, 2026
Pricing page
https://www.langchain.com/pricing
Supports: pricing_model, deployment_models
Developer, Plus, Enterprise; cloud US/EU, hybrid and self-hosted
checked Nov 1, 2026

Confidence: High
Reviewed: Nov 1, 2026
Links: Verified · Nov 2, 2026

Spotted an error?

LiteLLM

BerriAI · Prompting, evaluation & observability

Open-source Python SDK and self-hosted AI gateway that calls 100+ LLM providers in the OpenAI format, with routing, fallbacks, virtual keys, budgets, spend tracking and logging callbacks

MITOpen sourceFreeLocalSelf-hostedNov 2, 2026

OpenRouter

OpenRouter, Inc. · Model providers & APIs

Unified API gateway to hundreds of models from many providers with automatic fallbacks, credit-based pass-through billing, BYOK, free models and data-policy routing

ProprietaryFreemiumUsage-basedBroken

DSPy

Stanford NLP and the DSPy community · Prompting, evaluation & observability

Python framework for programming language-model pipelines with typed signatures and modules, then optimizing prompts and weights automatically against a metric