repowiserepowise

langchain-ai / langchain Architecture and code health

The agent engineering platform.

★ 149,351stars on GitHubPythonMITCurated

Repowise maps public repos from their source. Not affiliated with langchain-ai. What is Repowise?

github.com/langchain-ai/langchainIndexed at c6ec96aRefreshes weekly

What is langchain?

LangChain is a framework for building agents and LLM-powered applications. It chains together interoperable components and third-party integrations, such as model providers, tools, vector stores and retrievers, to simplify AI application development. Its code is written primarily in Python. To install it, run uv add langchain. Its code health is 6.8 out of 10 (Fair), ranked #134 of 4,000+ indexed repos. The last commit to langchain was on Nov 10, 2026, and 3,720 people have contributed.

As of commit c6ec96a, indexed Nov 11, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentslangchain.md

Repo facts: type, license, health, rank, contributors
langchain facts
LicenseMIT
Code health6.8 / 10 (Fair)
Health rank#134 of 4,000+ indexed repos
Last commitNov 10, 2026
Contributors3,720
Bus factor3
Size2,975 files, 329,788 lines

Install langchain

Commands copied from the README

  1. 1Install LangChain with uv
    uv add langchain

Releases on GitHub (latest langchain-core==1.8.0, Nov 11, 2026)

Full install notes on GitHub

Explore langchain

Ask about this code in your agent

This connects Repowise to langchain's code. It does not install langchain. To install langchain, use the install steps.

Useful if you want to change or fork langchain: your agent can ask how it is put together and get answers that cite its files.

Show the connect command (Claude Code, Cursor, Codex, VS Code)

Run it in a terminal, then type /mcp in Claude Code and sign in with Repowise. No key to paste.

Docs
bash
claude mcp add --transport http repowise https://api.repowise.dev/mcp/langchain-ai/langchain
Claude Code, Claude, Cursor and VS Code sign you in on first use, free. Codex and Windsurf need an API key: sign in to create one.Sign in for a key

This repo is public, so anyone with a free Repowise account can connect.

Try asking

  • get_risk(["libs/partners/anthropic/langchain_anthropic/chat_models.py"])
  • get_answer("how is langchain put together?")
  • get_why("why is langchain structured this way?")

Ask about langchain

Answers come from langchain's README and source, with the files they cite. Two free answers a day without an account.

Featured answer

LangChain is a framework for building agents and LLM-powered applications that chains together interoperable components and third-party integrations such as model providers, tools, vector stores and retrievers. Its code is written primarily in Python, and the repository contains 2975 files. Application code usually starts with a chat model created by init_chat_model, which takes a provider and model name such as openai:gpt-5.5, and calling its invoke method sends the request and returns the result. The shared components live in libs/core/langchain_core/init.py, which the langchain package entry point at libs/langchain_v1/langchain/init.py builds on, while provider integrations sit in separate packages under libs/partners, such as libs/partners/openai/langchain_openai/chat_models/base.py for OpenAI. The layer chart is led by the Application layer with 1449 files, followed by Utility with 234 and Service with 159, and to start reading you can begin with the two init.py entry points and then the partner packages, while the README describes LangGraph and LangSmith as separate products.

Files per layer in langchain8 layers.

Basis: Inferred · knowledge graph· as of c6ec96a

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of langchain-ai/langchain from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

langchain-ai/langchain FAQ

What is LangChain?

LangChain is a framework for building agents and LLM-powered applications. It chains together interoperable components and third-party integrations to simplify AI application development.

How does LangChain work?

LangChain provides a standard interface for models, embeddings, and vector stores. You create a chat model with init_chat_model, naming a provider and model such as openai:gpt-5.5, and then call invoke on it with a prompt.

How do I install LangChain?

Install LangChain with the command uv add langchain. This adds the langchain package to your project using uv. See the install steps

What language is LangChain written in?

LangChain is written primarily in Python. The repository also includes Makefile and shell scripts and a small amount of JavaScript.

How is the LangChain code organized?

The packages live under the libs directory. libs/core holds the langchain_core package, libs/langchain holds the langchain_classic package, and libs/partners holds provider integrations such as openai and anthropic.

Who is LangChain for?

LangChain is for developers building agents and LLM-powered applications who want standard interfaces to models and connections to external data sources through integrations.

What license does LangChain use?

LangChain is released under the MIT license, whose SPDX identifier is MIT.

Code health

6.8out of 10Fair

Hotspots average 3.5, the place fixes pay off most.

On the leaderboards:#4 of 5 Agent frameworks#39 of 64 Python repos

Key features of langchain

  • Chains together interoperable components and third-party integrations to simplify AI application development.
  • Provides a standard interface for models, embeddings, vector stores, and more.
  • Lets developers swap models in and out as their application needs change.
  • Connects LLMs to diverse data sources and external and internal systems through its integrations.
  • Supports monitoring, evaluation, and debugging of applications through integrations like LangSmith.

How langchain-ai/langchain works

Application code starts with a chat model created by init_chat_model, which takes a provider and model name such as openai:gpt-5.5 and returns a model object. Calling its invoke method with a prompt sends the request and returns the result. The libs/core/langchain_core/__init__.py file is the entry point of the langchain_core package, which holds the shared components the other packages build on. The libs/langchain_v1/langchain/__init__.py file is the entry point of the langchain package that the quickstart imports from. Provider integrations are kept in separate packages under libs/partners, where libs/partners/openai/langchain_openai/chat_models/base.py implements chat models for OpenAI and libs/partners/anthropic/langchain_anthropic/chat_models.py does the same for Anthropic. LangGraph for agent orchestration and LangSmith for evaluation and debugging are separate products that the README describes alongside the framework.

The codebase has 2,975 files and 20,802 symbols in 2 modules, led by Python, Makefile and Shell. Code health is 6.8 out of 10, rated fair.