automation

LangBot: Deploy Enterprise‑Grade Multi‑Channel AI Bots Quickly

Name: LangBot: Deploy Enterprise‑Grade Multi‑Channel AI Bots Quickly
Author: langbot-app

Launch AI‑powered assistants on Discord, Slack, WeChat, and more with built‑in LLM integrations and plugin orchestration. Ideal for founders scaling smart communication.

From the repo · “Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Kimi, openclaw / hermes agent, deerflow”

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

18,367 stars+204★ this week1,660 forksPythonGuide quality 9/10 · reviewed Oct 5Updated 10/21/2026100% free · open source

What it is

Build chatbots for multiple instant messaging platforms, like Discord or WeChat.

Real use case example

"A founder, Sarah, wants to create a community chatbot for her Discord server. She uses LangBot to connect her bot to multiple platforms, including Discord, and then configures it to respond to new members. After setting up the bot, Sarah notices an increase in engagement among her community members."

Best insideClaude DesktopClaude API

When to use it

•When you need to automate customer support on multiple messaging platforms
•When you want to integrate your chatbot with AI services like ChatGPT or DeepSeek
•When you need to build a custom bot for a specific messaging platform like Discord, Slack, or WeChat

Ready-to-paste prompt

Run the bot with ChatGPT integration: `python main.py --ai-provider chatgpt --ai-model gpt-3.5-turbo`

Heads up: You need to obtain API keys or credentials for the messaging platforms and AI services you want to integrate with, and set them up in the `config.yaml` file before running the bot

Saves to your device

Use with Claude

New

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

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/langbot && curl -fsSL https://workflowstacks.com/api/skills/langbot/claude-skill -o ~/.claude/skills/langbot/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 LangBot: Deploy Enterprise‑Grade Multi‑Channel AI Bots Quickly works

Codeflow

Free to inspect

LangBot: Deploy Enterprise‑Grade Multi‑Channel AI Bots Quickly is a very large Python project (~202k lines across 748 code files, plus 326 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~202k lines · 748 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Python · Docker

No API keys detected

Python 68%TypeScript 27%JavaScript 4%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
main.py
Where the program starts running
4
pyproject.toml
Dependencies and the commands it exposes
5
src/langbot/__init__.py
Inside src/ — the main logic begins here

What's in each folder

src/Core code — the actual logic613 files

skills/Prompts, skills & agent definitions216 files

web/Frontend / UI296 files

docs/Documentation30 files

examples/Examples you can copy8 files

res/Folder8 files

scripts/Helper scripts7 files

docker/Deployment / infrastructure3 files

READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month

Use with Claude

New

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

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/langbot && curl -fsSL https://workflowstacks.com/api/skills/langbot/claude-skill -o ~/.claude/skills/langbot/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

langbot-app

Language

Python

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Free n8n template

AI Support Agent (Chat)

A chat agent that answers customer questions from YOUR business info — with conversation memory. It never invents policies; anything it doesn't know, it hands to a human.

MCP config