Build context-aware reasoning applications with LangChain’s flexible abstractions and AI-first toolkits.

Core OSS libraries:

• LangChain and LangChain.js – reusable components and integrations for building LLM applications
• LangGraph and LangGraph.js – build LLM agents as graphs
• Deep Agents and Deep Agents.js – agents that can plan, use subagents, and leverage file systems for complex tasks

Commercial Platform:

• LangSmith – platform for building and monitoring production-grade LLM applications

OSS extensions and apps:

• Open SWE – open source asynchronous coding agent
• MCP Adapters – make MCP tools compatible with LangChain and LangGraph
• Open Canvas – document & chat-based UX for writing code or markdown. Inspired by OpenAI's Canvas (TypeScript)
• OpenGPTs – open source version of OpenAI's GPTs API (Python)
• Email assistant – AI assistant that helps you maintain your emails (Python)
• LangChain + Next.js template – template LangChain.js + Next.js application
• Social media agent – agent for sourcing, curating, and scheduling social media posts with human-in-the-loop (TypeScript)
• Agent Protocol – our attempt at codifying the framework-agnostic APIs that are needed to serve LLM agents in production

Learn more

• Documentation – unified docs for LangChain projects and services (source)
• Community forum – discuss, get help, and talk shop
• LangChain Academy – comprehensive, free courses on LangChain libraries and products, made by the LangChain team