agentic-aiCommunity canon

LangChain

Foundational composable library for chains, agents, and memory

View on GitHub

What it solves

The wiring problem in LLM development: connecting models to tools, data sources, and memory without writing glue code from scratch for every integration.

Overview

LangChain introduced the chain and agent primitives that the modern LLM ecosystem is built on. Core abstractions: chains (composable sequences of LLM calls), tools (functions an LLM can invoke by name), and memory (state that persists across turns). Most major frameworks (LangGraph, LangFlow, DeepAgents) layer on top of it rather than replacing it.

Key facts

Language
Python
License
MIT
Maturity
Community canon
Maintainer
langchain-ai
Reviewed
2026-06-11

Where to start

The agents concept doc explains the ReAct loop and tool-calling model that underpins every LangChain agent, read this before reaching for LangGraph.

docs/docs/concepts/agents.mdx

Technologies

langchainpython

More in this domain