Frameworks

What is LangChain?

LangChain is the most widely adopted toolkit for building LLM applications — components, integrations, and chains. What it is, where it sits against LangGraph, and what choosing it does and does not settle.

Agent Reality Index Ranked #1 in Frameworks 77.0 / 100 View ranking →

LangChain is an open-source framework for building applications around language models — the connective layer between a model and everything it needs to be useful: data sources, tools, memory, other models. It rose with the first wave of LLM applications by solving the unglamorous problem every team hit at once: the model is an API call, but the application is retrieval, parsing, tool invocation, and orchestration, and writing that plumbing bespoke for every project is waste. LangChain packaged the plumbing — and its integration catalogue, hundreds of connectors deep, remains the practical reason teams adopt it.

The framework's vocabulary maps cleanly to what you already know. Chains compose steps — prompt, model, parser, retrieval — into pipelines. Tools wrap capabilities the model may invoke, the same concept the Model Context Protocol now standardises across vendors. Memory carries state between turns. Agents, in LangChain's usage, are chains where the model chooses the next step — the agent loop in its toolkit form. For retrieval-heavy applications, the components assemble into the standard RAG architecture with unusually little code.

Where LangChain ends and LangGraph begins

The most common point of confusion is LangChain's relationship to LangGraph, its sibling from the same team. The short version: LangChain is the toolkit — components and integrations, control flow mostly linear and abstracted; LangGraph is the agent runtime — workflows as explicit graphs with first-class state, persistence, and human-approval stops. The full comparison draws the line in detail, but the practical reading is that the team's own centre of gravity for *agents* moved to LangGraph, with LangChain supplying the parts. If your system is a pipeline, LangChain alone is often enough; if it is an agent with consequences, you will probably end up drawing the graph.

What choosing LangChain settles — and what it cannot

A framework choice settles your development ergonomics: how fast integrations arrive, how much plumbing you skip, what your team debugs at 2am. It settles none of the readiness questions. A LangChain agent still needs its own identity and scoped credentials, evaluation before autonomy, a registry entry, and governance with names attached — the framework ships none of that, and no framework does. The frameworks landscape page makes the general argument: the framework is the most replaceable layer in an agentic system, so keep the durable parts — tools, evaluations, audit requirements — portable, and the cost of being wrong stays small.

Where to go from here

If you are evaluating frameworks, read the landscape and the LangChain–LangGraph comparison before committing. If you are building, the build guide sequences the work the framework does not do for you. And wherever the code lands, the maturity curve tells you whether the organisation around the code is ready for what it builds.

The explainer pages on what LangChain is and LangChain tools cover the framework's core concepts in depth.

Frequently asked questions

What is LangChain?

LangChain is an open-source framework for building applications around language models — the connective layer between a model and the data sources, tools, memory, and other models it needs. Its main draw is a large integration catalogue that saves teams from writing retrieval, parsing, and tool-invocation plumbing bespoke.

What is the difference between LangChain and LangGraph?

LangChain is the toolkit — components and integrations with mostly linear, abstracted control flow. LangGraph is the agent runtime — workflows as explicit graphs with first-class state, persistence, and human-approval stops. Pipelines often need only LangChain; agents with consequences usually end up drawing the graph.

Does choosing LangChain make my agents production-ready?

No. A framework settles development ergonomics, not readiness. A LangChain agent still needs its own identity and scoped credentials, evaluation before autonomy, a registry entry, and governance with names attached — none of which any framework ships.

Is LangChain still worth adopting?

For retrieval-heavy and integration-heavy applications, its connector catalogue remains the practical reason teams adopt it. Just treat the framework as the most replaceable layer and keep the durable parts — tools, evaluations, audit requirements — portable.

Is your organisation ready for AI agents?

Take the assessment →