LangBot Docs
Claude

Build a LINE AI Bot with Claude

Step-by-step guide to running a Claude-powered AI bot on LINE with LangBot: model setup, bot credentials, networking, testing and troubleshooting.

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

Use Anthropic's Claude models with LangBot's built-in Agent, including tool use with MCP servers, Skills and the code sandbox.

What you need

Networking

LINE calls a webhook, so LangBot needs a public HTTPS URL. LangBot Cloud includes a domain and HTTPS.

1. Add the Claude model

  1. Create an API key in the Anthropic console.
  2. In LangBot, open Models, add an LLM model with the provider set to Anthropic, then paste the API key and the model ID.
  3. Enable Tool Use if the model supports function calling; MCP tools, Skills and the sandbox need it.
  4. Keep the provider's default request URL unless you use a gateway. Use a current Claude model ID from Anthropic's documentation.

2. Create a pipeline

Open Pipelines in the LangBot WebUI, create a pipeline (or edit the default one) and set AI as follows.

FieldValue
RunnerLocal Agent (built-in Agent)
ModelThe model you just added. You can add fallback models.
PromptInstructions: who the bot is, tone, what it must not do.
Knowledge BasesOptional. Attach a knowledge base so answers come from your documents.

3. Create the LINE bot

  1. Create a bot with the LINE adapter and enter the Channel Secret and Channel Access Token.
  2. Copy the webhook callback URL from LangBot into the channel's Webhook URL, verify it, and turn on Use webhook.

4. Bind and test

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

Add the official account as a friend with its QR code and send a message.

Troubleshooting

  • The agent never calls tools: enable Tool Use on the model.
  • Webhook verification fails: check the URL and that HTTPS works from the public internet.
  • No replies: turn off LINE's auto-reply messages in the Official Account Manager so they do not answer instead of the bot.
  • 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 LINE?

Yes, or use LangBot Cloud. LINE calls a webhook, so LangBot needs a public HTTPS URL. LangBot Cloud includes a domain and HTTPS.

Does the LINE 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 Claude setup serve other platforms too?

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

Build a QQ Official Bot AI Bot with Claude

Step-by-step guide to running a Claude-powered AI bot on QQ Official Bot with LangBot: model setup, bot credentials, networking, testing and troubleshooting.

Build a KOOK AI Bot with Claude

Step-by-step guide to running a Claude-powered AI bot on KOOK with LangBot: model setup, bot credentials, networking, testing and troubleshooting.

On this page

What you needNetworking1. Add the Claude model2. Create a pipeline3. Create the LINE bot4. Bind and testTroubleshootingFAQDo I need a server with a public IP for LINE?Does the LINE bot support streaming replies?Can the same Claude setup serve other platforms too?Related guides