# Docs by LangChain: AGENT DEVELOPMENT LIFECYCLE Build Python > Documentation for LangSmith, Fleet, and our open source packages. ## Python ### Overview - [Build](https://docs.langchain.com/build-overview.md): Build agents with Managed Deep Agents, Deep Agents, LangChain, LangGraph, and Studio. ### Managed Deep Agents #### Get started - [Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-overview.md): Build your agent as a directory of files while LangSmith runs the harness and runtime. - [Managed Deep Agents quickstart](https://docs.langchain.com/langsmith/python/managed-deep-agents-quickstart.md): Create and deploy your first Managed Deep Agent with the mda CLI. - [Managed Deep Agents project structure](https://docs.langchain.com/langsmith/python/managed-deep-agents-project-structure.md): Understand the project layout for Managed Deep Agents. - [Move from Deep Agents to Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-migrate.md): Convert an agent built with create_deep_agent into a Managed Deep Agents project. #### Agent capabilities - [Define a Managed Deep Agent](https://docs.langchain.com/langsmith/python/managed-deep-agents-agent-definition.md): Configure the model and core capabilities of a managed deep agent. - [Add instructions to Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-instructions.md): Define the system prompt for a managed deep agent in instructions.md. - [Add skills to Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-skills.md): Add reusable task-specific instructions to a managed deep agent. - [Add custom tools to Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-tools.md): Define authored tools for managed deep agents projects. - [Web search](https://docs.langchain.com/langsmith/python/managed-deep-agents-search.md): Add web search powered by Parallel to Managed Deep Agents without a separate account or API key. - [Manage connections](https://docs.langchain.com/langsmith/python/managed-deep-agents-connections.md): Store API keys and OAuth grants so Managed Deep Agents can authenticate with external services at runtime. - [Connect to MCP servers](https://docs.langchain.com/langsmith/python/managed-deep-agents-mcp-connectors.md): Add tools from remote MCP servers to a managed deep agent. - [Add custom middleware to Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-middleware.md): Add built-in or custom middleware to a managed deep agent. - [Add memory to Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-memory.md): Opt in to durable agent and user memory layers for a managed deep agent. - [Add a sandbox to Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-sandboxes.md): Configure an isolated filesystem and shell for a managed deep agent. - [Browser use](https://docs.langchain.com/langsmith/python/managed-deep-agents-browser-use.md): Configure browser sharing, website logins, and human handoff for a managed deep agent. - [Subagents](https://docs.langchain.com/langsmith/python/managed-deep-agents-subagents.md): Delegate work to subagents that run inline or in the background for a managed deep agent. - [Add identity to Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-identity.md): Authenticate callers to a Managed Deep Agents deployment with a LangSmith API key, Supabase, another JWT provider, or your own backend. - [Add schedules to Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-schedules.md): Declare managed cron schedules for Managed Deep Agents deployments, or create them at runtime. - [Evaluate Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-evals.md): Develop Harbor evals for Managed Deep Agents with a coding agent and the eval-engineering skill. - [Managed Deep Agents runtime](https://docs.langchain.com/langsmith/python/managed-deep-agents-runtime.md): Read run context, the verified caller, the thread, and the sandbox from the native runtime types that agent factories, tools, and middleware receive. ##### Channels - [Connect Managed Deep Agents to channels](https://docs.langchain.com/langsmith/python/managed-deep-agents-channels.md): Connect Managed Deep Agents to external messaging services that can start runs and receive responses. - [Connect a Managed Deep Agent to Slack](https://docs.langchain.com/langsmith/python/managed-deep-agents-channels-slack.md): Start Managed Deep Agents runs from Slack messages and send responses to Slack conversations. - [Connect a Managed Deep Agent to a custom channel over HTTP](https://docs.langchain.com/langsmith/python/managed-deep-agents-channels-http.md): Start Managed Deep Agents runs from any external service that can send a webhook, and return responses through your own transport. - [Prompt Slack users with agent-owned interrupts](https://docs.langchain.com/langsmith/python/managed-deep-agents-agent-owned-interrupts.md): Post a Slack form from a Managed Deep Agents tool, pause the run, and resume it when the user submits the form. #### Build and deploy - [Develop locally with LangSmith Studio](https://docs.langchain.com/langsmith/python/managed-deep-agents-local-development.md): Run and test a Managed Deep Agent locally with mda dev and LangSmith Studio. - [Add a custom search tool, memory, and a schedule](https://docs.langchain.com/langsmith/python/managed-deep-agents-tutorial.md): Replace provider search with a Tavily tool, then add durable memory and a daily schedule to the research assistant from the quickstart. - [Deploy a Managed Deep Agent](https://docs.langchain.com/langsmith/python/managed-deep-agents-deploy.md): Test and deploy a Managed Deep Agent with the mda CLI. - [Connect MCP clients to a Managed Deep Agent](https://docs.langchain.com/langsmith/python/managed-deep-agents-mcp-endpoint.md): Expose a deployed Managed Deep Agent as a tool to MCP clients such as Claude Code. - [Build a custom frontend for a Managed Deep Agent](https://docs.langchain.com/langsmith/python/managed-deep-agents-custom-frontend.md): Call a Managed Deep Agents deployment from your own web or Python application with the LangChain frontend SDKs and the LangGraph SDK. - [Manage Context Hub for Managed Deep Agents](https://docs.langchain.com/langsmith/python/managed-deep-agents-context-hub.md): Understand how Managed Deep Agents stores instructions, skills, and durable memory in LangSmith Context Hub. - [Managed Deep Agents CLI reference](https://docs.langchain.com/langsmith/python/managed-deep-agents-cli.md): Reference for mda commands, project files, and deploy behavior. #### Templates - [Deploy the open-source design agent](https://docs.langchain.com/langsmith/python/managed-deep-agents-design-agent.md): Deploy Content Studio, an open-source design agent, to Slack as a Managed Deep Agents project. - [Deploy the open-source paid media agent](https://docs.langchain.com/langsmith/python/managed-deep-agents-paid-media-agent.md): Deploy the open-source paid media agent to Slack as a Managed Deep Agents project for campaign analysis, scheduled reports, and reviewed changes. ### Deep Agents - [Deep Agents overview](https://docs.langchain.com/oss/python/deepagents/overview.md): Agent harness for planning, subagents, and file-system context, available as Managed Deep Agents or the Deep Agents SDK #### Get started - [Quickstart](https://docs.langchain.com/oss/python/deepagents/quickstart.md): Build your first deep agent in minutes - [Customize Deep Agents](https://docs.langchain.com/oss/python/deepagents/customization.md): Learn how to customize Deep Agents with system prompts, tools, subagents, and more - [Models](https://docs.langchain.com/oss/python/deepagents/models.md): Configure model providers and parameters for Deep Agents - [Comparison with Claude Agent SDK](https://docs.langchain.com/oss/python/deepagents/comparison.md): Compare LangChain Deep Agents and Managed Deep Agents with the Claude Agent SDK to choose the right tool for your use case. #### Deployment ##### Going to production - [Going to production](https://docs.langchain.com/oss/python/deepagents/going-to-production.md): Take your deep agent to production with persistent memory, sandboxes, resilience middleware, and deployment options - [Fault tolerance](https://docs.langchain.com/oss/python/deepagents/fault-tolerance.md): Make your deep agent resilient with rate limiting, retries, fallbacks, and error handling #### Execution environment - [Tools](https://docs.langchain.com/oss/python/deepagents/tools.md): Connect Deep Agents to custom functions, APIs, databases, and any MCP server - [Backends](https://docs.langchain.com/oss/python/deepagents/backends.md): Choose and configure filesystem backends for Deep Agents. You can specify routes to different backends, implement virtual filesystems, and enforce policies. - [Permissions](https://docs.langchain.com/oss/python/deepagents/permissions.md): Control filesystem access with declarative permission rules for Deep Agents - [Multimodal inputs and outputs](https://docs.langchain.com/oss/python/deepagents/multimodal.md): Use images, audio, video, and documents with Deep Agents when your model supports multimodal inputs and tool results - [Sandboxes](https://docs.langchain.com/oss/python/deepagents/sandboxes.md): Execute code in isolated environments with sandbox backends - [Browser use](https://docs.langchain.com/oss/python/deepagents/browser-use.md): Give a deep agent a browser so it can take actions on websites and test web apps end to end. - [Interpreters](https://docs.langchain.com/oss/python/deepagents/interpreters.md): Run lightweight code inside Deep Agents to compose tools, orchestrate subagents, and transform structured data - [Event streaming](https://docs.langchain.com/oss/python/deepagents/event-streaming.md): Stream subagents, messages, tool calls, and final output from Deep Agents. - [Streaming](https://docs.langchain.com/oss/python/deepagents/streaming.md): Stream real-time updates from deep agent runs and subagent execution #### Context management - [Skills](https://docs.langchain.com/oss/python/deepagents/skills.md): Learn how to extend your deep agent's capabilities with skills - [Memory](https://docs.langchain.com/oss/python/deepagents/memory.md): Add persistent memory to agents built with Deep Agents so they learn and improve across conversations - [Retrieval](https://docs.langchain.com/oss/python/deepagents/retrieval.md) - [Context engineering in Deep Agents](https://docs.langchain.com/oss/python/deepagents/context-engineering.md): Control what context your deep agent has access to and how it is managed across long-running tasks - [Profiles](https://docs.langchain.com/oss/python/deepagents/profiles.md): Package per-provider and per-model defaults that Deep Agents applies when a model is selected #### Delegation - [Subagents](https://docs.langchain.com/oss/python/deepagents/subagents.md): Learn how to use subagents to delegate work and keep context clean - [Dynamic subagents](https://docs.langchain.com/oss/python/deepagents/dynamic-subagents.md): Use interpreters to dispatch and orchestrate Deep Agents subagents from code - [Async subagents](https://docs.langchain.com/oss/python/deepagents/async-subagents.md): Launch background subagents that run concurrently while the supervisor continues interacting with the user #### Steering - [Human-in-the-loop](https://docs.langchain.com/oss/python/deepagents/human-in-the-loop.md): Learn how to configure human approval for sensitive tool operations - [Grading rubrics](https://docs.langchain.com/oss/python/deepagents/rubric.md): LLM-as-a-judge grading for agents that iterate against a rubric until done #### Middleware - [Middleware overview](https://docs.langchain.com/oss/python/langchain/middleware/overview.md): Control and customize agent execution at every step - [Prebuilt middleware](https://docs.langchain.com/oss/python/langchain/middleware/built-in.md): Prebuilt middleware for common agent use cases - [Custom middleware](https://docs.langchain.com/oss/python/langchain/middleware/custom.md) #### Frontend - [Overview](https://docs.langchain.com/oss/python/deepagents/frontend/overview.md): Build UIs that display real-time subagent streams, task progress, and sandbox for Deep Agents ##### Patterns - [Subagent streaming](https://docs.langchain.com/oss/python/deepagents/frontend/subagent-streaming.md): Display specialist subagents with streaming content, progress tracking, and collapsible cards - [Todo list](https://docs.langchain.com/oss/python/deepagents/frontend/todo-list.md): Track agent progress with a real-time todo list synced from agent state - [Sandbox](https://docs.langchain.com/oss/python/deepagents/frontend/sandbox.md): Build an IDE-like UI for a coding agent backed by a sandbox environment #### Protocols - [Agent Client Protocol (ACP)](https://docs.langchain.com/oss/python/deepagents/acp.md): Expose Deep Agents over the Agent Client Protocol (ACP) to integrate with code editors and IDEs. - [Agent User Interaction Protocol (AG-UI)](https://docs.langchain.com/oss/python/deepagents/ag-ui.md): Expose deep agents over the Agent User Interaction Protocol (AG-UI) to stream events to any AG-UI client or frontend. ### LangChain - [LangChain overview](https://docs.langchain.com/oss/python/langchain/overview.md): LangChain provides create_agent: a minimal, highly configurable agent harness. Compose exactly the agent your use case needs from model, tools, prompt, and middleware. #### Get started - [Install LangChain](https://docs.langchain.com/oss/python/langchain/install.md): Install the LangChain package and the independent provider packages for the models and integrations you use. - [Quickstart](https://docs.langchain.com/oss/python/langchain/quickstart.md): Build your first agent in minutes - [Philosophy](https://docs.langchain.com/oss/python/langchain/philosophy.md): LangChain exists to be the easiest place to start building with LLMs, while also being flexible and production-ready. #### Core components - [Agents](https://docs.langchain.com/oss/python/langchain/agents.md): Build a LangChain agent: a model calling tools in a loop until a task is complete, shaped by a harness of prompt, tools, and middleware. - [Models](https://docs.langchain.com/oss/python/langchain/models.md): Initialize and configure chat models, the reasoning engine of LangChain agents, with support for tool calling, structured output, and multimodal inputs. - [Messages](https://docs.langchain.com/oss/python/langchain/messages.md) - [Tools](https://docs.langchain.com/oss/python/langchain/tools.md): Define tools that let LangChain agents fetch real-time data, execute code, query external databases, and take actions. - [Short-term memory](https://docs.langchain.com/oss/python/langchain/short-term-memory.md) - [Event streaming](https://docs.langchain.com/oss/python/langchain/event-streaming.md): Stream real-time updates from LangChain agent runs - [Streaming](https://docs.langchain.com/oss/python/langchain/streaming.md): Stream real-time updates from agent runs - [Structured output](https://docs.langchain.com/oss/python/langchain/structured-output.md) #### Middleware - [Middleware overview](https://docs.langchain.com/oss/python/langchain/middleware/overview.md): Control and customize agent execution at every step - [Prebuilt middleware](https://docs.langchain.com/oss/python/langchain/middleware/built-in.md): Prebuilt middleware for common agent use cases - [Custom middleware](https://docs.langchain.com/oss/python/langchain/middleware/custom.md) #### Frontend - [Overview](https://docs.langchain.com/oss/python/langchain/frontend/overview.md): Build generative UIs with real-time streaming from LangChain agents ##### Patterns - [Markdown messages](https://docs.langchain.com/oss/python/langchain/frontend/markdown-messages.md): Render LLM responses as rich, formatted markdown with proper streaming support - [Tool calling](https://docs.langchain.com/oss/python/langchain/frontend/tool-calling.md): Display agent tool calls with rich, type-safe UI cards - [Headless tools](https://docs.langchain.com/oss/python/langchain/frontend/headless-tools.md): Run browser and device APIs on the client with headless tool implementations - [Human-in-the-Loop](https://docs.langchain.com/oss/python/langchain/frontend/human-in-the-loop.md): Add approval workflows with interrupt-based human review - [Branching chat](https://docs.langchain.com/oss/python/langchain/frontend/branching-chat.md): Edit messages and regenerate responses by forking from checkpoints - [Reasoning tokens](https://docs.langchain.com/oss/python/langchain/frontend/reasoning-tokens.md): Display model thinking and reasoning processes in collapsible blocks - [Structured output](https://docs.langchain.com/oss/python/langchain/frontend/structured-output.md): Render structured agent responses with custom UI components instead of plain text - [Message queues](https://docs.langchain.com/oss/python/langchain/frontend/message-queues.md): Queue multiple messages and manage them while the agent processes sequentially - [Join & rejoin streams](https://docs.langchain.com/oss/python/langchain/frontend/join-rejoin.md): Disconnect from and reconnect to running agent streams - [Time travel](https://docs.langchain.com/oss/python/langchain/frontend/time-travel.md): Inspect, navigate, and resume from any checkpoint in the conversation history ###### Generative UI - [Generative UI overview](https://docs.langchain.com/oss/python/langchain/frontend/generative-ui-overview.md): Understand the generative UI spectrum from controlled to declarative to open-ended interfaces - [Controlled generative UI](https://docs.langchain.com/oss/python/langchain/frontend/controlled-generative-ui.md): Render agent output with components you author using components as tools, tool-call rendering, state rendering, and reasoning - [Declarative generative UI](https://docs.langchain.com/oss/python/langchain/frontend/declarative-generative-ui.md): Compose agent-generated interfaces from a registered component catalog using json-render and A2UI - [Open-ended generative UI](https://docs.langchain.com/oss/python/langchain/frontend/open-ended-generative-ui.md): Render UI created outside your application, such as sandboxed MCP Apps, at the open end of the generative UI spectrum ##### Integrations - [Overview](https://docs.langchain.com/oss/python/langchain/frontend/integrations/overview.md): Connect useStream to any React UI component library or generative UI framework - [CopilotKit](https://docs.langchain.com/oss/python/langchain/frontend/integrations/copilotkit.md): Use CopilotKit with LangGraph, Deep Agents, and React with custom endpoints, the Python AG-UI bridge, structured generative UI, and messaging-platform channels - [AI Elements](https://docs.langchain.com/oss/python/langchain/frontend/integrations/ai-elements.md): Composable shadcn/ui-based components for AI chat interfaces with useStream - [assistant-ui](https://docs.langchain.com/oss/python/langchain/frontend/integrations/assistant-ui.md): Headless React AI chat framework with a full runtime layer, bridged to useStream - [OpenUI](https://docs.langchain.com/oss/python/langchain/frontend/integrations/openui.md): Generate complete, interactive dashboards and reports using the OpenUI component library and openui-lang #### Advanced usage - [Guardrails](https://docs.langchain.com/oss/python/langchain/guardrails.md): Implement safety checks and content filtering for your agents - [Runtime](https://docs.langchain.com/oss/python/langchain/runtime.md) - [Context engineering in agents](https://docs.langchain.com/oss/python/langchain/context-engineering.md) - [Human-in-the-loop](https://docs.langchain.com/oss/python/langchain/human-in-the-loop.md) - [Retrieval](https://docs.langchain.com/oss/python/deepagents/retrieval.md) - [Long-term memory](https://docs.langchain.com/oss/python/langchain/long-term-memory.md): Add long-term memory to LangChain agents to store and recall data across conversations and sessions ##### MCP - [Model Context Protocol (MCP)](https://docs.langchain.com/oss/python/langchain/mcp/index.md): Connect LangChain agents to MCP servers with MCPAdapter. - [Tools](https://docs.langchain.com/oss/python/langchain/mcp/tools.md): Load MCP tools into LangChain agents, control their execution, and handle server results and requests. - [Connections](https://docs.langchain.com/oss/python/langchain/mcp/connections.md): Connection lifecycle, multiple servers, deployment scaling, protocol eras, and caching for MCP in LangChain. - [Authentication](https://docs.langchain.com/oss/python/langchain/mcp/auth.md): Authenticate MCP connections with bearer tokens, OAuth 2.1, or per-user credentials in LangChain. ##### Multi-agent - [Multi-agent](https://docs.langchain.com/oss/python/langchain/multi-agent/index.md) - [Subagents](https://docs.langchain.com/oss/python/langchain/multi-agent/subagents.md) - [Handoffs](https://docs.langchain.com/oss/python/langchain/multi-agent/handoffs.md) - [Skills](https://docs.langchain.com/oss/python/langchain/multi-agent/skills.md) - [Router](https://docs.langchain.com/oss/python/langchain/multi-agent/router.md) - [Custom workflow](https://docs.langchain.com/oss/python/langchain/multi-agent/custom-workflow.md) #### Agent development - [LangSmith Studio](https://docs.langchain.com/oss/python/langchain/studio.md) - [Agent Chat UI](https://docs.langchain.com/oss/python/langchain/ui.md) ##### Test - [Test](https://docs.langchain.com/oss/python/langchain/test/index.md): Strategies for testing LangChain agents, including unit tests, integration tests, and trajectory evaluations. - [Unit testing](https://docs.langchain.com/oss/python/langchain/test/unit-testing.md): Test agent logic without API calls using fake chat models and in-memory persistence. - [Integration testing](https://docs.langchain.com/oss/python/langchain/test/integration-testing.md): Test agents with real LLM APIs by organizing tests, managing keys, handling flakiness, and controlling costs. - [Agent Evals](https://docs.langchain.com/oss/python/langchain/test/evals.md): Evaluate agent trajectories using deterministic matching or LLM-as-judge evaluators with AgentEvals and LangSmith. #### Production - [Deployment](https://docs.langchain.com/oss/python/langchain/deploy.md): Deploy LangChain agents to production with LangSmith Cloud or JavaScript frameworks and hosting platforms. - [LangSmith Observability](https://docs.langchain.com/oss/python/langchain/observability.md) ### LangGraph - [LangGraph overview](https://docs.langchain.com/oss/python/langgraph/overview.md): Low-level orchestration framework and runtime for long-running, stateful agents #### Get started - [Quickstart](https://docs.langchain.com/oss/python/langgraph/quickstart.md) #### Capabilities - [Persistence](https://docs.langchain.com/oss/python/langgraph/persistence.md): LangGraph's persistence layer gives agents short-term memory through checkpointers and long-term memory through stores. - [Checkpointers](https://docs.langchain.com/oss/python/langgraph/checkpointers.md): LangGraph checkpointers save graph state as checkpoints at each step, enabling persistence, human-in-the-loop, and fault-tolerant execution. - [Stores](https://docs.langchain.com/oss/python/langgraph/stores.md): LangGraph stores provide cross-thread long-term memory, complementing per-thread checkpointer persistence. - [Fault tolerance](https://docs.langchain.com/oss/python/langgraph/fault-tolerance.md): Configure per-node timeouts, retries, error handlers, and recovery strategies in LangGraph. - [Event streaming](https://docs.langchain.com/oss/python/langgraph/event-streaming.md): Stream LangGraph runs with typed projections for messages, state, subgraphs, output, and extensions. - [Streaming](https://docs.langchain.com/oss/python/langgraph/streaming.md) - [Interrupts](https://docs.langchain.com/oss/python/langgraph/interrupts.md) - [Use time-travel](https://docs.langchain.com/oss/python/langgraph/use-time-travel.md): Replay past executions and fork to explore alternative paths in LangGraph - [Memory](https://docs.langchain.com/oss/python/langgraph/add-memory.md) - [Subgraphs](https://docs.langchain.com/oss/python/langgraph/use-subgraphs.md) #### Patterns - [Workflows and agents](https://docs.langchain.com/oss/python/langgraph/workflows-agents.md) #### Build with the Graph API - [Thinking in the Graph API](https://docs.langchain.com/oss/python/langgraph/thinking-in-graph-api.md): Learn how to design agents with the LangGraph Graph API using nodes, edges, and shared state. - [Build checklist for the Graph API](https://docs.langchain.com/oss/python/langgraph/use-graph-api.md): Decide state, control flow, Send, Command, and node options as you build with the Graph API. - [Graph API overview](https://docs.langchain.com/oss/python/langgraph/graph-api.md): Learn how LangGraph models agent workflows as graphs of shared state, nodes, and edges. - [Define and update state](https://docs.langchain.com/oss/python/langgraph/graph-api-state.md): Define graph state schemas, reducers, messages, and private state in the LangGraph Graph API. - [Build sequences, branches, and loops](https://docs.langchain.com/oss/python/langgraph/graph-api-control-flow.md): Compose sequences, parallel branches, conditional edges, and loops with the LangGraph Graph API. - [Use Send and Command](https://docs.langchain.com/oss/python/langgraph/graph-api-send-command.md): Build map-reduce workflows with Send and combine state updates with routing using Command in LangGraph. - [Configure nodes](https://docs.langchain.com/oss/python/langgraph/graph-api-nodes.md): Add runtime configuration, retry policies, timeouts, error handling, defaults, and caching to LangGraph nodes. - [Visualize your graph](https://docs.langchain.com/oss/python/langgraph/graph-api-visualize.md): Render LangGraph graphs as Mermaid diagrams or PNG images for debugging and documentation. #### Deployment - [Run a local server](https://docs.langchain.com/oss/python/langgraph/local-server.md) - [Application structure](https://docs.langchain.com/oss/python/langgraph/application-structure.md) - [Test](https://docs.langchain.com/oss/python/langgraph/test.md) - [Backward compatibility](https://docs.langchain.com/oss/python/langgraph/backward-compatibility.md): Update LangGraph graph code in production without breaking in-flight runs. - [LangSmith Studio](https://docs.langchain.com/oss/python/langgraph/studio.md) - [Agent Chat UI](https://docs.langchain.com/oss/python/langgraph/ui.md) - [Deployment](https://docs.langchain.com/oss/python/langgraph/deploy.md): Deploy LangGraph agents to production with LangSmith Cloud or JavaScript frameworks and hosting platforms. - [LangSmith Observability](https://docs.langchain.com/oss/python/langgraph/observability.md) #### Frontend - [Overview](https://docs.langchain.com/oss/python/langgraph/frontend/overview.md): Render LangGraph agents to the frontend - [Graph execution](https://docs.langchain.com/oss/python/langgraph/frontend/graph-execution.md): Visualize multi-step graph pipelines with per-node status and streaming content - [Custom stream channels](https://docs.langchain.com/oss/python/langgraph/frontend/custom-stream-channels.md): Stream custom server-side data to the frontend and read it with useExtension and useChannel #### Advanced - [Functional API overview](https://docs.langchain.com/oss/python/langgraph/functional-api.md): Wrap other frameworks with entrypoints and tasks for LangSmith Agent Server. Covers checkpointing, resume rules, and common pitfalls. - [LangGraph runtime](https://docs.langchain.com/oss/python/langgraph/pregel.md) ### OpenWiki - [OpenWiki](https://docs.langchain.com/oss/openwiki/overview.md): CLI that writes and maintains agent wikis so coding agents work faster - [Quickstart](https://docs.langchain.com/oss/openwiki/quickstart.md): Install OpenWiki, configure a model provider, and generate your first wiki. - [Coding-agent integrations](https://docs.langchain.com/oss/openwiki/integrations.md): Run OpenWiki inside Codex, Claude Code, GitHub Copilot, OpenCode, Cursor, IBM Bob, Kiro, Oh My Pi, or Antigravity using the host model and tools - [Search and link wikis](https://docs.langchain.com/oss/openwiki/search-and-link.md): Search OpenWiki pages over MCP and group related repository wikis into workspaces - [Visualize your wiki](https://docs.langchain.com/oss/openwiki/visualize.md): Explore an OpenWiki Markdown wiki with a local interactive node graph and reader - [Command reference](https://docs.langchain.com/oss/openwiki/cli-reference.md): OpenWiki command-line usage, flags, and connector subcommands - [Customize OpenWiki](https://docs.langchain.com/oss/openwiki/customize.md): Ignore paths, wiki instructions, agent pointers, and telemetry for OpenWiki - [Model providers](https://docs.langchain.com/oss/openwiki/providers.md): Configure inference providers and credentials for OpenWiki - [Automate updates](https://docs.langchain.com/oss/openwiki/automate-updates.md): Schedule OpenWiki documentation updates with GitHub Actions, GitLab CI, or Bitbucket Pipelines #### Modes - [Code mode](https://docs.langchain.com/oss/openwiki/code-mode.md): Generate and maintain repository documentation for coding agents with OpenWiki - [Personal mode](https://docs.langchain.com/oss/openwiki/personal-mode.md): Build a local personal brain wiki from configured sources with OpenWiki. ### Integrations - [LangChain Python integrations](https://docs.langchain.com/oss/python/integrations/providers/overview.md): Integrate with providers using LangChain Python. - [All LangChain Python integration providers](https://docs.langchain.com/oss/python/integrations/providers/all_providers.md) #### Popular Providers - [OpenAI integrations](https://docs.langchain.com/oss/python/integrations/providers/openai.md): Integrate with OpenAI using LangChain Python. - [Anthropic (Claude) integrations](https://docs.langchain.com/oss/python/integrations/providers/anthropic.md): Integrate with Anthropic (Claude) using LangChain Python. - [Google integrations](https://docs.langchain.com/oss/python/integrations/providers/google.md): Integrate with Google using LangChain Python. - [AWS (Amazon) integrations](https://docs.langchain.com/oss/python/integrations/providers/aws.md): Integrate with AWS (Amazon) using LangChain Python. - [NVIDIA](https://docs.langchain.com/oss/python/integrations/providers/nvidia.md): Integrate with NVIDIA using LangChain Python. - [Hugging Face integrations](https://docs.langchain.com/oss/python/integrations/providers/huggingface.md): Integrate with Hugging Face using LangChain Python. - [Microsoft integrations](https://docs.langchain.com/oss/python/integrations/providers/microsoft.md): Integrate with Microsoft using LangChain Python. - [Ollama integrations](https://docs.langchain.com/oss/python/integrations/providers/ollama.md): Integrate with Ollama using LangChain Python. - [Groq integrations](https://docs.langchain.com/oss/python/integrations/providers/groq.md): Integrate with Groq using LangChain Python. - [Fireworks integrations](https://docs.langchain.com/oss/python/integrations/providers/fireworks.md): Integrate with Fireworks AI using LangChain Python. - [Browserbase integrations](https://docs.langchain.com/oss/python/integrations/providers/browserbase.md): Integrate with Browserbase using LangChain Python. #### Integrations by component - [Chat model integrations](https://docs.langchain.com/oss/python/integrations/chat/index.md): Integrate with chat models using LangChain Python. - [Tool integrations](https://docs.langchain.com/oss/python/integrations/tools/index.md): Integrate with tools using LangChain Python. - [Middleware integrations](https://docs.langchain.com/oss/python/integrations/middleware/index.md): Integrate with middleware using LangChain Python. - [Sandbox integrations](https://docs.langchain.com/oss/python/integrations/sandboxes/index.md): Integrate with sandbox providers using LangChain Python. - [Backend integrations](https://docs.langchain.com/oss/python/integrations/backends/index.md): Filesystem backends for Deep Agents. - [Checkpointer integrations](https://docs.langchain.com/oss/python/integrations/checkpointers/index.md): Integrate with checkpointer backends for LangGraph persistence. - [Store integrations](https://docs.langchain.com/oss/python/integrations/long-term-memory/index.md): Integrate with store backends for LangGraph long-term memory. - [Retriever integrations](https://docs.langchain.com/oss/python/integrations/retrievers/index.md): Integrate with retrievers using LangChain Python. - [Text splitter integrations](https://docs.langchain.com/oss/python/integrations/splitters/index.md): Integrate with text splitters using LangChain. - [Embedding model integrations](https://docs.langchain.com/oss/python/integrations/embeddings/index.md): Integrate with embedding models using LangChain Python. - [Vector store integrations](https://docs.langchain.com/oss/python/integrations/vectorstores/index.md): Integrate with vector stores using LangChain Python. - [Document loader integrations](https://docs.langchain.com/oss/python/integrations/document_loaders/index.md): Integrate with document loaders using LangChain Python. ### Learn - [Learn](https://docs.langchain.com/oss/python/learn.md): Tutorials, conceptual guides, and resources to help you get started. #### Tutorials ##### Deep Agents - [Build a data analysis agent](https://docs.langchain.com/oss/python/deepagents/data-analysis.md): Build an agent that analyzes data files, generates visualizations, and shares results - [Build a deep research agent](https://docs.langchain.com/oss/python/deepagents/deep-research.md): Build a multi-step web research agent with subagent delegation using Managed Deep Agents or the Deep Agents SDK - [Build a content builder agent](https://docs.langchain.com/oss/python/deepagents/content-builder.md): Build a content writing agent with brand voice, skills, subagents, and image generation using Managed Deep Agents or the Deep Agents SDK - [Retrieval Augmented Generation (RAG) with Deep Agents](https://docs.langchain.com/oss/python/deepagents/rag.md): RAG patterns for Deep Agents, including skills-guided retrieval, rubric grading, and a tutorial that indexes LangChain docs, offloads chunks to the filesystem, and delegates analysis to subagents ##### LangChain - [Build a data analysis agent from scratch](https://docs.langchain.com/oss/python/langchain/deep-agent-from-scratch.md): Build a data analysis agent step by step using create_agent and Deep Agents middleware. - [Build a semantic search engine with LangChain](https://docs.langchain.com/oss/python/langchain/knowledge-base.md) - [Build a SQL agent](https://docs.langchain.com/oss/python/langchain/sql-agent.md) - [Build a voice agent with LangChain](https://docs.langchain.com/oss/python/langchain/voice-agent.md) ##### Multi-agent - [Build a personal assistant with subagents](https://docs.langchain.com/oss/python/langchain/multi-agent/subagents-personal-assistant.md) - [Build customer support with handoffs](https://docs.langchain.com/oss/python/langchain/multi-agent/handoffs-customer-support.md) - [Build a multi-source knowledge base with routing](https://docs.langchain.com/oss/python/langchain/multi-agent/router-knowledge-base.md) - [Build a SQL assistant with on-demand skills](https://docs.langchain.com/oss/python/langchain/multi-agent/skills-sql-assistant.md) ##### LangGraph - [Build a custom RAG agent with LangGraph](https://docs.langchain.com/oss/python/langgraph/agentic-rag.md): Build a custom retrieval agent with LangGraph that decides when to search a vector store or respond directly. - [Build a custom SQL agent](https://docs.langchain.com/oss/python/langgraph/sql-agent.md) #### Conceptual overviews - [Runtimes, frameworks, and harnesses](https://docs.langchain.com/oss/python/concepts/products.md): Understand the differences between LangChain, LangGraph, and Deep Agents and when to use each one - [Providers and models](https://docs.langchain.com/oss/python/concepts/providers-and-models.md): Understand how LangChain uses providers to give you a single API for any model from any provider - [Component architecture](https://docs.langchain.com/oss/python/langchain/component-architecture.md) - [Memory overview](https://docs.langchain.com/oss/python/concepts/memory.md) - [Context overview](https://docs.langchain.com/oss/python/concepts/context.md) - [Human-in-the-loop overview](https://docs.langchain.com/oss/python/concepts/human-in-the-loop.md): How agents pause tool calls for human review, and how per-call and batched interrupts differ. - [Graph API overview](https://docs.langchain.com/oss/python/langgraph/graph-api.md): Learn how LangGraph models agent workflows as graphs of shared state, nodes, and edges. - [Functional API overview](https://docs.langchain.com/oss/python/langgraph/functional-api.md): Wrap other frameworks with entrypoints and tasks for LangSmith Agent Server. Covers checkpointing, resume rules, and common pitfalls. #### Additional resources - [Use docs programmatically](https://docs.langchain.com/use-these-docs.md): Connect LangChain documentation to your AI tools and workflows - [Case studies](https://docs.langchain.com/oss/python/langgraph/case-studies.md) - [Get help](https://docs.langchain.com/oss/python/langchain/get-help.md) ### Reference - [Reference](https://docs.langchain.com/oss/python/reference/overview.md) #### Reference - [Errors](https://docs.langchain.com/oss/python/common-errors.md) #### Releases - [Versioning](https://docs.langchain.com/oss/python/versioning.md) - [Changelog](https://docs.langchain.com/oss/python/releases/changelog.md): Log of updates and improvements to our Python packages ##### Releases - [What's new in LangChain v1](https://docs.langchain.com/oss/python/releases/langchain-v1.md) - [What's new in LangGraph v1](https://docs.langchain.com/oss/python/releases/langgraph-v1.md) ##### Migration guides - [LangChain v1 migration guide](https://docs.langchain.com/oss/python/migrate/langchain-v1.md) - [LangGraph v1 migration guide](https://docs.langchain.com/oss/python/migrate/langgraph-v1.md) - [Migrate from langgraph-supervisor](https://docs.langchain.com/oss/python/migrate/langgraph-supervisor.md): Migrate from the langgraph-supervisor package to the subagents pattern with create_agent and tool-wrapped subagents. - [Migrate from langchain-mcp-adapters](https://docs.langchain.com/oss/python/migrate/langchain-mcp-adapters.md): Migrate from the standalone langchain-mcp-adapters package to the built-in langchain.mcp namespace. #### Policies - [Release policy](https://docs.langchain.com/oss/python/release-policy.md) - [Security policy](https://docs.langchain.com/oss/python/security-policy.md) ### Contribute - [Contributing](https://docs.langchain.com/oss/python/contributing/overview.md) #### Contribute - [Contributing to documentation](https://docs.langchain.com/oss/python/contributing/documentation.md) - [Contributing to code](https://docs.langchain.com/oss/python/contributing/code.md) ##### Integrations - [Contributing integrations](https://docs.langchain.com/oss/python/contributing/integrations-langchain.md) - [Implement a LangChain integration](https://docs.langchain.com/oss/python/contributing/implement-langchain.md) - [Using standard tests](https://docs.langchain.com/oss/python/contributing/standard-tests-langchain.md) - [Publish an integration](https://docs.langchain.com/oss/python/contributing/publish-langchain.md) - [Co-marketing](https://docs.langchain.com/oss/python/contributing/comarketing.md)