Repolode
Submit
langchain-ai

langchain-ai/chat-langchain

A documentation assistant agent that answers questions about LangChain, LangGraph, and LangSmith, built as a Managed Deep Agent with a Next.js chat UI.

View on GitHubWebsite
Stars
6,474
Forks
1,493
Open issues
536
Last commit
8 hours ago

What is it?

Chat LangChain is a documentation assistant that answers questions about LangChain, LangGraph, and LangSmith. It is designed as a reference implementation for building a production-style agent with LangChain agents, middleware, and guardrails that keep conversations on-topic.

The agent follows a docs-first strategy: it checks that a query is related to LangChain, searches the official documentation through a managed MCP connector, looks up known issues in a Pylon support knowledge base, and validates URLs before including them in answers. Deployment, identity, and connectors are handled by the Managed Deep Agents runtime, using Supabase tokens for signed-in and anonymous users.

The repository contains the Python backend, a prompt and tools layout, and a Next.js public chat frontend in a separate directory. It can be run locally with uv and a local Managed Deep Agent dev server.

Key features

  • 01Searches official LangChain, LangGraph, and LangSmith docs via a managed MCP connector.
  • 02Looks up known issues and solutions in a Pylon support knowledge base.
  • 03Validates URLs before including them in responses.
  • 04Filters off-topic queries with guardrails middleware.
  • 05Includes a Next.js chat frontend with Supabase-based sign-in and anonymous access.

Use cases

  • Getting answers to LangChain or LangGraph questions grounded in official documentation.
  • Studying a reference implementation of a docs-search agent with guardrails and middleware.
  • Adapting the pattern to build a documentation assistant for another product.

Quick start

  1. 1

    Clone the repository

    git clone https://github.com/langchain-ai/chat-langchain.git
  2. 2

    Change into the project directory

    cd chat-langchain
  3. 3

    Install Python dependencies with uv

    uv sync
  4. 4

    Copy the environment template and add your API keys in .env

    cp .env.example .env

Things to know

  • Requires several API keys, including an Anthropic key and Pylon credentials, before it runs.
  • Depends on managed services such as Managed Deep Agents and Supabase, so self-hosting takes extra setup.
  • Built specifically for LangChain, LangGraph, and LangSmith documentation questions.

In collections

AI chatbots & chat clients

Topics

#ai#agent#langchain#llm#rag#chatbot#typescript#python

FAQ

What is chat-langchain?
A documentation assistant agent that answers questions about LangChain, LangGraph, and LangSmith, built as a Managed Deep Agent with a Next.js chat UI. Chat LangChain is a documentation assistant that answers questions about LangChain, LangGraph, and LangSmith. It is designed as a reference implementation for building a production-style agent with LangChain agents, middleware, and guardrails that keep conversations on-topic.
Is chat-langchain free to use? What license does it have?
chat-langchain is open source under the MIT license. Check the license terms before using it in commercial products.
Is chat-langchain still maintained?
Actively maintained. The last commit to chat-langchain was on Nov 6, 2026.
What can I use chat-langchain for?
Getting answers to LangChain or LangGraph questions grounded in official documentation. Studying a reference implementation of a docs-search agent with guardrails and middleware. Adapting the pattern to build a documentation assistant for another product.
How do I install chat-langchain?
Clone the repository: git clone https://github.com/langchain-ai/chat-langchain.git Change into the project directory: cd chat-langchain Install Python dependencies with uv: uv sync Copy the environment template and add your API keys in .env: cp .env.example .env
Where can I get chat-langchain?
The source code and installation instructions are on GitHub: https://github.com/langchain-ai/chat-langchain

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects