# LangChain

> Open-source Python and TypeScript framework whose create_agent builds a configurable agent harness from a model, tools, a prompt and middleware.

- id: `langchain`
- category: Harnesses (`harnesses`)
- url: https://docs.langchain.com/oss/python/langchain/overview
- repo: https://github.com/langchain-ai/langchain
- docs: https://docs.langchain.com/oss/javascript/langchain/overview
- status: active
- pricing: open-source
- license: MIT
- tags: framework, python, typescript, agents, middleware
- llms.txt: https://docs.langchain.com/llms.txt
- related: LangGraph (https://indexagentica.com/entries/langgraph/); Deep Agents (LangChain) (https://indexagentica.com/entries/deepagents/); LangSmith (https://indexagentica.com/entries/langsmith/); LangChain Docs MCP (https://indexagentica.com/entries/langchain-docs-mcp/)
- sources: https://github.com/langchain-ai/langchain , https://docs.langchain.com/oss/python/langchain/overview , https://pypi.org/project/langchain/ , https://github.com/langchain-ai/langchainjs
- added: 2026-11-02
- updated: 2026-11-02
- last verified: 2026-11-02
- maintainer: LangChain
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/langchain/
- json: https://indexagentica.com/api/entries/langchain.json

LangChain's docs position it between LangGraph (low-level orchestration) and Deep Agents (batteries-included harness); LangSmith handles tracing and evals. Python package `langchain` 1.4.7 on PyPI (MIT, Python >=3.10); JS/TS lives in langchain-ai/langchainjs (npm `langchain` 1.6.0, MIT). The docs publish an llms.txt and two remote docs MCP servers (see langchain-docs-mcp).