Looking for the JS/TS version? Check out LangChain.js.
To help you ship LangChain apps to production faster, check out LangSmith. LangSmith is a unified developer platform for building, testing, and monitoring LLM applications.
uv add langchainLangChain is the easiest way to start building agents and applications powered by LLMs. With under 10 lines of code, you can connect to OpenAI, Anthropic, Google, and more. LangChain provides a pre-built agent architecture and model integrations to help you get started quickly and seamlessly incorporate LLMs into your agents and applications.
We recommend you use LangChain if you want to quickly build agents and autonomous applications. Use LangGraph, our low-level agent orchestration framework and runtime, when you have more advanced needs that require a combination of deterministic and agentic workflows, heavy customization, and carefully controlled latency.
LangChain agents are built on top of LangGraph in order to provide durable execution, streaming, human-in-the-loop, persistence, and more. (You do not need to know LangGraph for basic LangChain agent usage.)
For full documentation, see the API reference. For conceptual guides, tutorials, and examples on using LangChain, see the LangChain Docs. You can also chat with the docs using Chat LangChain.
See our Releases and Versioning policies.
As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
For detailed information on how to contribute, see the Contributing Guide.
Typed sync handle for a nested named-agent execution.
Typed async handle for a nested named-agent execution.
Promote nested named agents into typed handles on run.subagents.
Base class for structured output errors.
Raised when model returns multiple structured output tool calls when only one is expected.
Raised when structured output tool call arguments fail to parse according to the schema.
Use a tool calling strategy for model responses.
Use the model provider's native structured output method.
Information for tracking structured output tool metadata.
Information for tracking native structured output metadata.
Automatically select the best strategy for structured output.
Agent state extension for tracking shell session resources.
Structured result from command execution.
Persistent shell session that supports sequential command execution.
Middleware that registers a persistent shell tool for agents.
Middleware that automatically retries failed model calls with configurable backoff.
Configuration contract for persistent shell sessions.
Run the shell directly on the host process.
Launch the shell through the Codex CLI sandbox.
Run the shell inside a dedicated Docker container.
Model request information for the agent.
Response from model execution including messages and optional structured output.
Model response with an optional 'Command' from 'wrap_model_call' middleware.
Annotation used to mark state attributes as omitted from input or output schemas.
State schema for the agent.
Input state schema for the agent.
Output state schema for the agent.
Base middleware class for an agent.
Emulates specified tools using an LLM instead of executing them.
A single todo item with content and status.
State schema for the todo middleware.
Input schema for the write_todos tool.
Middleware that provides todo list management capabilities to agents.
Protocol describing a context editing strategy.
Configuration for clearing tool outputs when token limits are exceeded.
Automatically prune tool results to manage context size.
Middleware that automatically retries failed tool calls with configurable backoff.
State schema for ToolCallLimitMiddleware.
Exception raised when tool call limits are exceeded.
Track tool call counts and enforces limits during agent execution.
Uses an LLM to select relevant tools before calling the main model.
Keep internal model calls out of run.messages and the raw event log.
Provides Glob and Grep search over filesystem files.
Detect and handle Personally Identifiable Information (PII) in conversations.
Dictionary-based trigger specification for AND conditions.
Summarizes conversation history when token limits are approached.
Represents an action with a name and args.
Represents an action request with a name, args, and description.
Policy for reviewing a HITL request.
Request for human feedback on a sequence of actions requested by a model.
Response when a human approves the action.
Response when a human edits the action.
Response when a human rejects the action.
Response when a human answers on behalf of the tool, skipping execution.
Response payload for a HITLRequest.
Configuration for an action requiring human in the loop.
Human in the loop middleware.
Return selected tool-execution exceptions to the model as error ToolMessages.
Automatic fallback to alternative models on errors.
Defer selected tools behind provider-native tool search.
State schema for ModelCallLimitMiddleware.
Exception raised when model call limits are exceeded.
Tracks model call counts and enforces limits.
Represents an individual match of sensitive data.
Raised when configured to block on detected sensitive values.
Configuration for handling a single PII type.
Resolved redaction rule ready for execution.
A request for data matching a schema.
A request for the human to visit an address.
Interrupt payload raised while an MCP tool call waits on input.
An answer to an MCPElicitationRequest.
A refusal to answer an MCPElicitationRequest, leaving the call to go on.
A refusal that abandons the tool call rather than just the question.
Value used to resume a run interrupted by an MCP elicitation.
Artifact attached to the ToolMessage produced by an MCP tool call.
Adapt an MCP target into LangChain tools.
Initialize an embedding model from a model name and optional provider.
Creates an agent graph that calls tools in a loop until a stopping condition is met.
Validate retry parameters.
Return whether an exception should be retried by default.
Check if an exception should trigger a retry.
Calculate delay for a retry attempt with exponential backoff and optional jitter.
Decorator to configure hook behavior in middleware methods.
Decorator used to dynamically create a middleware with the before_model hook.
Decorator used to dynamically create a middleware with the after_model hook.
Decorator used to dynamically create a middleware with the before_agent hook.
Decorator used to dynamically create a middleware with the after_agent hook.
Decorator used to dynamically generate system prompts for the model.
Create middleware with wrap_model_call hook from a function.
Create middleware with wrap_tool_call hook from a function.
Create and manage a structured task list for your current work session.
Return metadata that marks a model call as internal to middleware.
Fast file pattern matching tool that works with any codebase size.
Fast content search tool that works with any codebase size.
Detect email addresses in content.
Detect credit card numbers in content using Luhn validation.
Detect IPv4 or IPv6 addresses in content.
Detect MAC addresses in content.
Detect URLs in content using regex and stdlib validation.
Apply the configured strategy to matches within content.
Return a callable detector for the given configuration.
Set the process-wide default TracePolicy for agent middleware hook spans.
Convert one MCP tool into a LangChain tool.
Initialize a chat model from any supported provider using a unified interface.
Main entrypoint into LangChain.
Tools.
Utils file included for backwards compat imports.
Base abstraction and in-memory implementation of rate limiters.
Embeddings models.
Factory functions for embeddings.
Entrypoint to building Agents with LangChain.
Types for setting agent response formats.
Agent factory for creating agents with middleware support.
Entrypoint to using middleware plugins with Agents.
Middleware that exposes a persistent shell tool to agents.
Model retry middleware for agents.
Types for middleware and agents.
Tool emulator middleware for testing.
Planning and task management middleware for agents.
Context editing middleware.
Tool retry middleware for agents.
Tool call limit middleware for agents.
LLM-based tool selector middleware.
Tag and filter middleware-internal model calls.
File search middleware for Anthropic text editor and memory tools.
PII detection and handling middleware for agents.
Summarization middleware.
Human in the loop middleware.
Tool error middleware for agents.
Model fallback middleware for agents.
Provider-side tool search middleware.
Call tracking middleware for agents.
LangChain MCP adapters for connecting MCP servers with LangChain applications.
Answer MCP elicitation requests with a LangGraph interrupt.
Convert MCP tools and tool results into LangChain-native values.
Adapt MCP tools into LangChain tools suitable for create_agent.
Message and message content types.
Entrypoint to using chat models in LangChain.
Factory functions for chat models.
Union type for all supported response format strategies.
Type for specifying which exceptions to retry on.
Type for specifying failure handling behavior.
Return type for model call handlers.
Behavior when the selection model keeps returning a malformed response.
Union type for context size specifications.
Tool name or tool instance that can be deferred behind provider tool search.
Values a form answer may carry, as narrow as mcp.types.ElicitResult.content.
One question an MCP server asks before finishing a tool call. Narrow on mode.
One answer to an MCPElicitationRequest. Narrow on action; only accept carries content.
LangChain content blocks an MCP tool result can convert into.
Anything MCPAdapter accepts as its target.