Skip to main content
LangSmith is a framework-agnostic platform for developing, debugging, and deploying AI agents and LLM applications. It helps you trace requests, evaluate outputs, test prompts, and manage deployments in one place. LangSmith works with any agent stack, whether you’re using an existing framework or building your own. Prototype locally, then move to production with integrated monitoring and evaluation to build more reliable AI agents.

​
Get started

Create an account

Sign up at smith.langchain.com (no credit card required). You can log in with Google, GitHub, or email.

Create an API key

Go to your Settings page → API Keys → Create API Key. Copy the key and save it securely.

Choose your integration

LangSmith works with many frameworks and providers including OpenAI, Anthropic, CrewAI, Vercel AI SDK, Pydantic AI, and more. Browse available integrations to connect your stack.
Once your account and API key are ready, choose a quickstart to begin building with LangSmith:
https://mintcdn.com/langchain-5e9cc07a/nQm-sjd_MByLhgeW/images/brand/observability-icon-dark.png?fit=max&auto=format&n=nQm-sjd_MByLhgeW&q=85&s=ccbc183bca2a5e4ca78d30149e3836cc

Observability

Gain visibility into every step your application takes to debug faster and improve reliability.
https://mintcdn.com/langchain-5e9cc07a/nQm-sjd_MByLhgeW/images/brand/evaluation-icon-dark.png?fit=max&auto=format&n=nQm-sjd_MByLhgeW&q=85&s=4918f932fff73a33d6a24e2fcf68f6a4

Evaluation

Measure and track quality over time to ensure your AI applications are consistent and trustworthy.
https://mintcdn.com/langchain-5e9cc07a/nQm-sjd_MByLhgeW/images/brand/deployment-icon-dark.png?fit=max&auto=format&n=nQm-sjd_MByLhgeW&q=85&s=024e3712d388bfa55f4f160cc9d6a85b

Deployment

Deploy your agents as Agent Servers, ready to scale in production.

​
More ways to build

https://mintcdn.com/langchain-5e9cc07a/_jaNDz0QENsVkDXY/images/brand/fleet-icon-dark.png?fit=max&auto=format&n=_jaNDz0QENsVkDXY&q=85&s=98e3bbb4ae01325a8ff867e80681778f

Fleet

Design and deploy AI agents visually with a no-code interface—perfect for rapid prototyping and getting started without writing code.
https://mintcdn.com/langchain-5e9cc07a/nQm-sjd_MByLhgeW/images/brand/prompt-engineering-icon.png?fit=max&auto=format&n=nQm-sjd_MByLhgeW&q=85&s=eaa7ac978bebe5a7cd84d8eeaaef84c2

Prompt engineering

Iterate on prompts with built-in versioning and collaboration to ship improvements faster.

Platform setup

Use LangSmith in managed cloud, in a self-hosted environment, or hybrid to match your infrastructure and compliance needs.

Studio

Use a visual interface to design, test, and refine applications end-to-end.
LangSmith meets the highest standards of data security and privacy with HIPAA, SOC 2 Type 2, and GDPR compliance. For more information, see the Trust Center.

​
Workflow

LangSmith combines observability, evaluation, deployment, and platform setup in one integrated workflow—from local development to production. Diagram showing how LangSmith integrates observability, evaluation, deployment, and platform setup in a single workflow from development to production.
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.