📖 Overview
LangBot is an open-source instant messaging bot platform supporting Feishu, DingTalk, WeChat, QQ, Telegram, Discord, Slack, and more. It connects mainstream AI models with knowledge base, Agent, and MCP capabilities.
⚙️ Connect to BeeHears
BeeHears is a New API–compatible relay. In most apps, fill in the three fields below using a token from the BeeHears console:
| Field | Value |
|---|---|
| API Base URL | https://ai.beehears.com or https://ai.beehears.com/v1 (use the OpenAI-compatible field the app expects) |
| API Key | BeeHears console token (starts with sk-) |
| Model name | A model ID available on your account (list via /v1/models). |
Create a token at https://ai.beehears.com and confirm model access. Never paste secrets into docs or chat.
BeeHears does not own this third-party app. Steps below are adapted from upstream New API docs for BeeHears (ai.beehears.com).
📚 Setup guide
LangBot is an open-source instant messaging bot development platform that
supports various instant messaging platforms such as Feishu, DingTalk, WeChat,
QQ, Telegram, Discord, Slack, etc. It integrates with mainstream global AI
models, supports various AI application capabilities like Knowledge Base,
Agent, MCP, and is perfectly compatible with BeeHears.
- Official Website: https://langbot.app
- Download Address: https://github.com/langbot-app/LangBot/releases
- Official Documentation: https://docs.langbot.app
- Open Source Address: https://github.com/langbot-app/LangBot
Integrating BeeHears
LangBot supports integrating with locally deployed BeeHears and third-party BeeHears services built using BeeHears.
Usage
- Obtain an API key from BeeHears
If BeeHears is deployed locally, please configure the API address yourself (refer to Container Network Connection). If using a third-party BeeHears service, you can copy the address from the page. Note that /v1 needs to be appended to the address.
- Add a model in LangBot, select BeeHears as the provider, and fill in the corresponding API key and API address
- Select the model to use in the pipeline
- Use it by chatting in conversation debugging or by chatting with a bot bound to the pipeline
For deploying and configuring bots, please refer to Deploying Bots.
Using LangBot Knowledge Base
LangBot supports using BeeHears's embedding models and utilizing them as vector models for the knowledge base.
- Add an embedding model in LangBot, select BeeHears as the provider
- Select the embedding model when creating a new knowledge base
For more usage instructions, please refer to the LangBot official documentation: https://docs.langbot.app