langchain
Building applications with LLMs through composability
Decision gist · record as of 2026-08-14
Yes. LangChain is production-stable, actively maintained, permissively licensed, and widely adopted. Install friction is low and security vulnerabilities are zero. It is the right choice if you want to quickly build and iterate on LLM applications; use langgraph directly if you need lower-level control over agent orchestration.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- Most use cases also require installing a model provider integration separately to connect to an LLM.
- Low friction install with a pure Python wheel.
License · maintenance · safety
MIT (permissive) — MIT license (permissive) allows commercial and private use with minimal restrictions; you may use, modify, and distribute LangChain freely provided you include the license notice.
last release 2026-08-11 (3 days) · last repo commit 2026-08-14 · 144,194 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 315,426,291 downloads/mo, #133 on PyPI
Alternatives
Verify before relying
pip install langchain
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
prompt = ChatPromptTemplate.from_template("Hello {name}")
chain = prompt | output_parser- Whether the package includes built-in integrations or if all model providers require separate installation.
- Performance characteristics and latency under typical agent workloads.
- Compatibility and interaction patterns with langgraph for advanced orchestration scenarios.
What it is and what it does
LangChain is a framework for composing language model applications. It sits on top of langchain-core (the base abstractions), langgraph (the agent runtime), and pydantic (for data validation), providing a higher-level API for building agents and chained LLM workflows. The package lets you connect to multiple model providers through a unified interface, so you can swap providers or combine models without rewriting application logic.
The framework is designed for rapid prototyping and production deployment of LLM-powered systems. It handles common patterns like prompt templating, output parsing, memory management, and agent loops. For simpler use cases, LangChain provides pre-built agent architectures; for more complex workflows requiring fine-grained control over deterministic and agentic logic, the documentation recommends using langgraph directly.
Use it for
- Build a chatbot or Q&A agent that queries external APIs or databases and returns structured responses.
- Chain multiple LLM calls with intermediate reasoning steps, memory, and tool use.
- Prototype an autonomous agent that can plan, execute actions, and iterate based on feedback.
- Integrate LLM capabilities into an existing application with minimal boilerplate.
- Experiment with different model providers without changing application code.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
LangChain is production-stable, actively maintained, permissively licensed, and widely adopted. Install friction is low and security vulnerabilities are zero. It is the right choice if you want to quickly build and iterate on LLM applications; use langgraph directly if you need lower-level control over agent orchestration.
Install
langchain on PyPI
Before you install
Low friction install with a pure Python wheel. Actively maintained—released 3 days ago with 144194 repository stars and last commit on 2026-08-14. Supports Python 3.10 through 3.14.
Requires Python 3.10 or later. Most use cases also require installing a model provider integration separately to connect to an LLM.
License in practice
MIT license (permissive) allows commercial and private use with minimal restrictions; you may use, modify, and distribute LangChain freely provided you include the license notice.
Quickstart
pip install langchain
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
prompt = ChatPromptTemplate.from_template("Hello {name}")
chain = prompt | output_parserVerify before relying
- Whether the package includes built-in integrations or if all model providers require separate installation.
- Performance characteristics and latency under typical agent workloads.
- Compatibility and interaction patterns with langgraph for advanced orchestration scenarios.
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 packageslangchain-corelanggraphpydantic |
| Maintenance | Actively maintained 3 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 315,426,291 / month, #133 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | 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 |
Evidence: langchain-1.3.15-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “llm chains and agents”
- langchainLangChain provides a framework for building agents and LLM-powered…
- langchain-coreLangChain Core provides the foundational abstractions and interfaces…
- langchain-cerebrasIntegrates Cerebras AI inference services with LangChain, enabling…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also alita-sdk · kosong · langchain-azure-ai · langchain-cli · langchain-core · langchain-experimental · langchain-mcp-adapters · langgraph · langserve · lunary