langchain-ai/langchain

What is it?

Key features

• 01Standard interfaces for chat models, embeddings, vector stores, retrievers and tools.
• 02Single-call model initialization across multiple providers such as OpenAI, Anthropic and Gemini.
• 03Large library of third-party integrations for model providers, tools and data sources.
• 04Layered abstractions, from high-level quickstart components to low-level control.
• 05Works with LangGraph, Deep Agents and LangSmith for orchestration and observability.

Use cases

• Building a retrieval-augmented generation (RAG) app that answers questions over private documents.
• Prototyping an LLM feature and swapping between model providers without rewriting application code.
• Creating tool-using agents that call external APIs or internal systems.
• Adding LLM capabilities to a Python backend while keeping a consistent interface.

Quick start

1. 1

   Install LangChain with uv

   uv add langchain
2. 2

   Initialize a chat model and invoke it (set the matching provider API key first)

   python -c "from langchain.chat_models import init_chat_model; model = init_chat_model('openai:gpt-5.5'); print(model.invoke('Hello, world!'))"

Things to know

• !Calling most models requires a paid API key from a model provider.

Topics

FAQ

What is langchain?

A Python framework for building LLM-powered applications and agents, with standard interfaces for models, embeddings, vector stores and third-party integrations. LangChain is a framework for building agents and LLM-powered applications. It lets developers chain together interoperable components and third-party integrations so that application code does not have to be rewritten each time the underlying model or provider changes.

Is langchain free to use? What license does it have?

langchain is open source under the MIT license. Check the license terms before using it in commercial products.

Is langchain still maintained?

Actively maintained. The last commit to langchain was on Oct 20, 2026.

What can I use langchain for?

Building a retrieval-augmented generation (RAG) app that answers questions over private documents. Prototyping an LLM feature and swapping between model providers without rewriting application code. Creating tool-using agents that call external APIs or internal systems. Adding LLM capabilities to a Python backend while keeping a consistent interface.

How do I install langchain?

Install LangChain with uv: uv add langchain Initialize a chat model and invoke it (set the matching provider API key first): python -c "from langchain.chat_models import init_chat_model; model = init_chat_model('openai:gpt-5.5'); print(model.invoke('Hello, world!'))"

Where can I get langchain?

The source code and installation instructions are on GitHub: https://github.com/langchain-ai/langchain