support

Langchain-Chatchat: Local LLM App

Name: Langchain-Chatchat: Local LLM App
Author: chatchat-space

Get a local knowledge-based LLM app for chatbot development, ideal.

intermediate⏱ 1-2 hours💵 Free (self-hosted)

38,562 stars6,263 forksPythonGuide quality 8/10Updated 11/10/2025100% free · open source

What it is

Build a local knowledge-based chatbot application using Langchain-Chatchat, a Python-based tool.

Real use case example

"A founder of a small e-commerce startup wants to automate customer support. They use Langchain-Chatchat to build a chatbot that answers questions about products and shipping, by integrating it with their local product database. After setting it up, customers can now get instant answers to common questions, freeing up the founder to focus on other tasks."

When to use it

•You want to create a custom chatbot that leverages your own data and knowledge base.
•You need an AI-powered support tool that can understand and respond to user queries in a specific domain or industry.
•You prefer to keep your data and AI models local, rather than relying on cloud-based services.

Ready-to-paste prompt

python scripts/chat.py -m ChatGLM -kg my_knowledge_graph.json -a my_agent.json

Heads up: Before running Langchain-Chatchat, ensure you have a compatible local LLM model installed, such as ChatGLM or Llama, and that the model's API is properly configured and accessible.

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/langchain-chatchat && curl -fsSL https://workflowstacks.com/api/skills/langchain-chatchat/claude-skill -o ~/.claude/skills/langchain-chatchat/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Langchain-Chatchat: Local LLM App works

Codeflow

Free to inspect

Langchain-Chatchat: Local LLM App is a large Python project (~25k lines across 260 code files, plus 33 test files). Setup is light: runs with Docker. Last commit 10 months ago, Apache-2.0 license, has a test suite.

Size

Large codebase

~25k lines · 260 code files · ~3 h to skim

Setup

Light setup

Runs with Docker.

Runs on

Python · Docker

No API keys detected

Python 99%Shell 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
pyproject.toml
Dependencies and the commands it exposes

What's in each folder

docs/Documentation43 files

libs/Folder358 files

markdown_docs/Folder91 files

tools/Helper scripts9 files

docker/Deployment / infrastructure4 files

.github/CI / automation (GitHub Actions)10 files

READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseLast update 10 mo ago

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/langchain-chatchat && curl -fsSL https://workflowstacks.com/api/skills/langchain-chatchat/claude-skill -o ~/.claude/skills/langchain-chatchat/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

chatchat-space

Language

Python