LangChain
A framework for building applications and agents on top of large language models.
- Stars
- 149k
- Forks
- 25.1k
- Licence
- MIT
- Language
- Python
- Updated
At a glance
- Standard interfaces for chat models, embeddings, retrievers and tools
- Hundreds of provider and vector-store integrations
- Agent building blocks with tool calling and memory
Get started
pip install langchainWhat it is
LangChain gives a common interface to the pieces most LLM applications are built from: models, prompts, retrievers, tools and agents. Swapping one model provider for another is a configuration change rather than a rewrite.
Why it stands out
Its breadth is the draw. The integration catalogue covers most commercial and open model providers, vector databases and document loaders, so a prototype can be wired together quickly.
Who it is for
Python developers building retrieval-augmented generation, chatbots or tool-using agents.
