LangSmith
langchain.com
- Free plan
- Windows
- macOS
- Linux
- Web
- API
- Self-hosted
What LangSmith is
LangSmith is a commercial platform for building, testing, deploying, monitoring, and improving AI agents. It supports offline evaluations on curated datasets and online scoring of production interactions in real time. Evaluation methods include human review, heuristic checks, LLM-as-judge evaluators, pairwise comparisons, and custom Python or TypeScript evaluators. Annotation queues route runs to subject-matter experts for calibration, prompt improvement, or dataset augmentation. The Playground compares prompt versions or model providers, and LangSmith chat can improve prompts automatically. Observability includes agent tracing, retrieval tracing, cost and token tracking, trajectory monitoring, online evaluations, and webhook or PagerDuty alerts. SDKs are listed for Python, TypeScript, Go, and Java, with native tracing and OpenTelemetry support. Traces can come through an SDK or API from LangGraph, custom Python, or other stacks. Developer costs nothing, Plus costs $39 a month, and Enterprise pricing is custom. Cloud, hybrid, and self-hosted deployment options are listed.
Who it suits
LangSmith suits teams engineering AI agents that need evaluation, tracing, prompt workflows, and production monitoring. Its framework-agnostic SDK and deployment choices support varied application stacks.
Good to know, and what to watch
- Supports offline and real-time evaluations
- Offers human and LLM-based evaluators
- Includes agent and retrieval tracing
- Integrates with pytest, Vitest, and GitHub
- Provides cloud, hybrid, and self-hosted options
- Base traces have 14-day retention
- Extended trace retention costs extra
Plans
Every plan and priceEnterprise
Developer
Plus
Free plan
The verdict
LangSmith combines evaluation, prompt iteration, observability, and deployment support for AI-agent teams. The free Developer tier is available, while retention limits and usage-based charges require planning.
What the maker publishes
- API and CLI
- LangSmith exposes a REST API and a CLI that manages projects, traces, runs, datasets, evaluators, experiments, threads and sandboxes. source
- CI/CD
- The evaluation workflow integrates with pytest, Vitest and GitHub workflows for automated regression checks. source
- CLI installation
- The CLI provides installation paths for macOS, Linux and Windows through shell scripts, PowerShell, Homebrew, Scoop, Go or downloadable binaries. source
- Company origins
- LangChain says the company began in early 2023 and that LangSmith launched first as a commercial observability product before expanding into evaluation and deployment. source
- Company profile
- LinkedIn lists LangChain as privately held, headquartered in San Francisco, with 201–500 employees and 469 employees shown on the page. source
- Data residency
- Cloud data is hosted in GCP US or EU regions, while self-hosted data remains in the customer's VPC. source
- Data use
- The pricing page says LangSmith does not use customer data to train models and that traces, prompts, and outputs remain private to the organization. source
- Data use
- LangChain states that LangSmith data is not used to train models and remains owned by the customer. source
- Deployment
- Deployment provides managed or self-hosted agent servers with streaming, cron scheduling, authentication, MCP support and more than 30 API endpoints. source
- Documentation
- LangChain publishes reference documentation, integration guides, deployment instructions, a CLI guide and a REST API reference. source
- Evaluation
- It supports offline evaluations on curated datasets and online evaluations that score production interactions in real time. source
- Evaluation
- Evaluation supports offline datasets, online production evaluations, human annotation queues and side-by-side experiment comparison. source
- Evaluators
- Its evaluation framework supports human review, heuristic checks, LLM-as-judge evaluators, pairwise comparisons, and custom evaluators in Python or TypeScript. source
- Evaluator types
- Evaluators can be human, heuristic, LLM-as-judge, pairwise or custom Python and TypeScript code. source
- Founded
- 2023 source
- Framework support
- LangSmith is framework-agnostic and accepts traces through its SDK or API from LangGraph, custom Python, or other application stacks. source
- Funding
- LangChain announced a $125 million Series B at a $1.25 billion valuation on October 20, 2025. source
- Headquarters
- San Francisco, California, United States source
- Hosting
- The pricing page lists Cloud hosting for Developer and Plus, with Cloud, Hybrid, or Self-Hosted options for Enterprise. source
- Human feedback
- Annotation queues let teams assign runs to subject-matter experts and use feedback to calibrate evaluations, improve prompts, or augment datasets. source
- Integrations
- The evaluation page says LangSmith integrates with pytest, Vitest, and GitHub workflows for evaluations in CI/CD pipelines. source
- Integrations
- Documented integrations cover OpenAI, Anthropic, Bedrock, Gemini, Mistral, LiteLLM, OpenTelemetry, CrewAI, Vercel AI SDK, PydanticAI, AutoGen and many other frameworks and providers. source
- Legal entity
- Crunchbase identifies the maker as LangChain, Inc., a privately held San Francisco company founded by Harrison Chase and Ankush Gola. source
- Limit: deployment documentation
- A LangChain forum user reported authentication failures and difficulty understanding deployment secrets, assistant IDs and setup documentation. source
Checked against the maker's pages on 15 Oct 2026.