LangSmith
LangChain's agent and LLM observability and evaluation platform: tracing, monitoring, cost and latency tracking.
Tags
Description
Client SDKs: as of 2026-10-16 the langchain-ai/langsmith-sdk monorepo is archived; the Python SDK now lives in langchain-ai/langsmith-python and the JS/TS SDK in langchain-ai/langsmith-javascript (both MIT). Package names are unchanged (langsmith on PyPI and npm).
Agent access
Related
- LangGraph: Low-level orchestration framework from LangChain for building resilient, stateful agents as graphs.
- Langfuse: Open-source agent evals and observability platform: trace, evaluate and improve LLM applications and agents.
- LangSmith Remote MCP: LangSmith-hosted MCP server exposing conversation history, prompts, runs and traces, datasets, experiments and billing; OAuth or API key.
Guides & comparisons
- Observability and eval platforms for AI agents (Comparison): Langfuse, LangSmith, Arize Phoenix, Braintrust, Opik and Laminar compared on license, self-hosting, OpenTelemetry ingestion, MCP access to your traces, free tiers, paid entry prices and built-in evaluation.
- Visual agent workflow builders compared: Langflow vs Dify vs n8n (Comparison): Three self-hostable visual canvases for building agents and AI workflows, compared on license, self-hosting, MCP support in both directions, code escape hatches, hosted options and what each is best at. Includes a note on Flowise, whose repo is archived.
Sources
- https://www.langchain.com/langsmith
- https://docs.langchain.com/langsmith/observability
- https://github.com/langchain-ai/langsmith-sdk
- https://github.com/langchain-ai/langsmith-python
- https://github.com/langchain-ai/langsmith-javascript
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)