Skip to main content
LangSmith provides integrations for a growing set of popular LLM providers and agent frameworks as well as Deep Agents, LangChain, and LangGraph. For setup and usage, refer to the guides listed on this page. Before sending traces in an agent-based workspace, create an agent and choose its environment. Complete this setup once, then follow the tracing guide for your integration.

​
LLM providers

Amazon BedrockAnthropicDeepSeekGoogle GeminiLiteLLMMistralOpenAIOpenAI-compatible APIs
Using LangChain? LangChain provides a unified interface to 100+ LLM providers, which allows you to switch between models by setting environment variables. Initialize a model and LangSmith will automatically trace your agent.

​
Agent frameworks

AutoGenClaude Agent SDKClaude Managed AgentsCrewAIDeep AgentsGoogle ADKLangChainLangGraphMastraMicrosoft Agent FrameworkOpenAI AgentsOpenTelemetryPydanticAISemantic KernelStrands AgentsVercel AI SDK

​
Voice AI frameworks

OpenAI RealtimeGemini LiveLivekitPipecat

​
Developer tools

Claude CodeOpenAI CodexOpenCodeCursorInstructorn8nPiTemporalVS Code Copilot
These coding agent integrations follow a shared metadata contract that standardizes the trace fields they emit.
Connect these docs to your agent of choice via MCP for real-time answers.
Edit this page on GitHub or file an issue.