LangChain

license

MIT(langchain-core,langgraph,integrations)

commercial

LangSmith-platform/cloud

source

public

core features withheld

no — every package in langchain-ai/langchain is MIT with no enterprise directory

Every package in the langchain-ai/langchain repository is MIT licensed, and a full recursive listing finds no enterprise, ee or commercial directory anywhere in the tree. LangSmith, sold separately for observability, evaluation and deployment, adds nothing the published packages lack, so a paid product beside the framework does not gate its core.

• https://github.com/langchain-ai/langchain recorded 2026-08-15

  Repository page for langchain-ai/langchain: 'MIT license' in the sidebar, 144.2k stars, public and unarchived. Establishes the licence and that the source is public.

• https://pypi.org/pypi/langchain/json recorded 2026-09-29

  The PyPI metadata for langchain carries the classifier "License :: OSI Approved :: MIT License".

• https://raw.githubusercontent.com/langchain-ai/langchain/master/LICENSE recorded 2026-09-29

  The root LICENSE of the public langchain-ai/langchain repository is the MIT License: "MIT License" and "Copyright (c) LangChain, Inc." followed by "Permission is hereby granted, free of charge, to any person obtaining a copy".

• https://raw.githubusercontent.com/langchain-ai/langchain/master/README.md recorded 2026-09-29

  The README says the framework runs alone, "While the LangChain framework can be used standalone", and lists LangSmith separately for "Agent evals, observability, and debugging for LLM apps".

• https://www.langchain.com/langchain recorded 2026-09-29

  The vendor page titles the product "Open Source AI Agent Framework for Any Model"; searched the body for a paid framework tier or license key: none.

• https://www.langchain.com/pricing recorded 2026-09-29

  The pricing page is titled "LangSmith Plans and Pricing" and lists langchain only under "Open Source"; searched the body for a paid tier of the langchain library itself: none.

Adoption is measured by PyPI downloads of the langchain package, the channel through which the framework is mainly distributed. Because the package is the product itself rather than an SDK for a hosted service, this count measures use of the framework itself, not a proxy for it.

• https://grokipedia.com/page/LangChain recorded 2026-08-13

  background on the framework and its ecosystem (corroborating, not the basis)

• https://pypistats.org/api/packages/langchain/recent recorded 2026-08-13

  281,508,705 downloads in the trailing 30 days for langchain

• https://www.langchain.com/langchain recorded 2026-08-13

  LangChain presented as the open source framework, with LangSmith sold separately (corroborating, not the basis)

Broadest LLM/agent orchestration ecosystem: chains, LangGraph stateful agent graphs, hundreds of model/tool integrations. No single benchmark for the framework; rated on feature breadth.

• https://github.com/langchain-ai/langchain recorded 2026-08-13

  chains, agents and the integration ecosystem published in full under MIT; no benchmark figure

• https://raw.githubusercontent.com/langchain-ai/langchain/master/README.md recorded 2026-09-29

  The README describes "LangChain is a framework for building agents and LLM-powered applications" and lists LangGraph, Deep Agents and integrations as companion packages.

• https://www.langchain.com/langchain recorded 2026-09-29

  The vendor page describes LangChain as "the open source framework with pre-built agent architectures and 1,000+ integrations"; no benchmark figure is published.