langchain

Building applications with LLMs through composability

langchain Permissive license MIT Active ★ 144,174 v1.3.15 released 2026-08-11

Install

langchain on PyPI

pip

pip install langchain

uv

uv add langchain

poetry

poetry add langchain

Package facts

License	MIT (permissive)
Python support	supports the current Python release (<4.0.0,>=3.10.0)
Install friction	low — pure-Python wheel
Runtime dependencies	3 — langchain-core, langgraph, pydantic
Maintenance	actively maintained — 2 days since the last release
Last repo commit	2026-08-13
First released	2022-10-25
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: langchain-1.3.15-py3-none-any.whl

Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Software Development :: Libraries :: Python Modules

About langchain

from the package's own PyPI description — quoted content, verbatim

🦜️🔗 LangChain

PyPI - Version (image) PyPI - License (image) PyPI - Downloads (image) Twitter (image)

Looking for the JS/TS version? Check out LangChain.js.

To help you ship LangChain apps to production faster, check out LangSmith. LangSmith is a unified developer platform for building, testing, and monitoring LLM applications.

Quick Install

uv add langchain

🤔 What is this?

LangChain is the easiest way to start building agents and applications powered by LLMs. With under 10 lines of code, you can connect to OpenAI, Anthropic, Google, and more. LangChain provides a pre-built...

Read as markdown · JSON record · Source repository · Homepage · Docs

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

LangChain is a framework for building LLM-powered agents and applications by composing language model integrations, retrieval systems, and tool orchestration with minimal boilerplate.

Low friction: pure Python wheel with only 3 runtime dependencies (langchain-core, langgraph, pydantic). Active maintenance with release 2 days old and continuous repository activity signal strong upkeep.

MIT license (permissive) allows commercial and private use with minimal restrictions—you may use, modify, and distribute freely provided you include the license notice.

Usage

pip install langchain

from langchain_core import BaseLanguageModel
from langgraph import StateGraph

# Requires a language model provider configured separately

Requires Python 3.10 or later; a language model provider (OpenAI, Anthropic, etc.) must be configured separately via environment variables or explicit credentials.

Verdict: LangChain is a mature, actively maintained framework (Production/Stable, 2-day-old release) with low install friction and no known vulnerabilities. MIT licensing poses no restrictions. Suitable for rapid prototyping of LLM agents; production use benefits from careful dependency management of the three core runtime packages.

Needs verification

Community size and adoption metrics beyond repository activity.
Performance characteristics and latency overhead compared to direct language model API calls.
Stability guarantees or breaking-change policy across minor version increments.

llm agent frameworkbuild chatbot with language modelsopenai integration pythonretrieval augmented generationautonomous agent orchestrationprompt chaining frameworkagentic workflow builder