Connect Langflow to KOOK

This recipe puts your Langflow app behind a KOOK bot. LangBot receives messages from KOOK, runs them through a pipeline, and sends the answer back, so you do not write any platform code.

Langflow builds agents and flows with a drag-and-drop editor. LangBot runs a flow through the Langflow API for every message.

What you need

• A running LangBot instance: LangBot Cloud (no server needed) or a self-hosted deployment with Docker or uvx langbot.
• A Langflow account or instance that LangBot can reach over the network.
• A bot created in the KOOK developer center and its Bot Token.

Networking

The KOOK adapter only needs a bot token; LangBot connects out to KOOK.

1. Prepare Langflow

1. Build a flow in Langflow (the Simple Agent template is a good start).
2. Create an API key under Settings.
3. Copy the Flow ID from Share → API access.

2. Create a pipeline

Open Pipelines in the LangBot WebUI, create a pipeline (or edit the default one) and set AI as follows. If the runner is not listed, install the official runner plugin from Plugins or the LangBot Space marketplace.

3. Create the KOOK bot

1. Create a bot with the KOOK adapter and enter the Bot Token.
2. Grant the bot permissions and invite it to your server.

4. Bind and test

Open the bot, select the pipeline you created, save and make sure the bot is enabled.

Send a message that matches the trigger rules in a channel the bot can read.

Troubleshooting

• Connection refused: http://localhost:7860 only works when Langflow runs on the same host and network namespace as LangBot.
• No reply in a channel: check the bot's channel permissions and the pipeline's group trigger rules.
• Check Monitoring in the WebUI: every message, pipeline run and error is recorded there.

FAQ

Do I need a server with a public IP for KOOK?

No. The KOOK adapter only needs a bot token; LangBot connects out to KOOK.

Does the KOOK bot support streaming replies?

Check the platform feature matrix for what this platform supports. Replies are delivered once the AI back end has finished.

Can the same Langflow setup serve other platforms too?

Yes. A pipeline can be bound to many bots, so one configuration can answer on several platforms at once.

Related guides

• Full KOOK setup guide
• Full Langflow runner guide
• Other AI back ends on KOOK: Dify · n8n · Coze · DeepSeek · OpenAI (ChatGPT models)
• Langflow on other platforms: Telegram · Discord · Slack · Lark (Feishu) · DingTalk · WeCom (internal app)