Build a Discord AI Bot with Ollama

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

Run open models locally with Ollama and serve them through LangBot's built-in Agent, so conversations never leave your machines.

What you need

• A running LangBot instance: LangBot Cloud (no server needed) or a self-hosted deployment with Docker or uvx langbot.
• A Ollama account or server you can call from LangBot.
• A Discord application with a bot: its Client ID and bot token from the Developer Portal, with Server Members Intent and Message Content Intent enabled.

Networking

Discord bots connect out to the Discord gateway, so no public webhook URL is required.

1. Add the Ollama model

1. Install Ollama and pull a model (for example ollama pull followed by the model name).
2. In LangBot, open Models and add an LLM model with the provider set to Ollama and the request URL pointing at your Ollama server (by default port 11434).
3. If LangBot runs in Docker, localhost is the container itself: use the host's address (for example host.docker.internal) instead.

2. Create a pipeline

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

3. Create the Discord bot

1. Create a bot with the Discord adapter and enter the Client ID and token.
2. Invite the bot from OAuth2 → URL Generator with the bot scope and Guild Install, granting permission to view channels and send messages.

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 server channel, then try a DM from the bot's profile.

Troubleshooting

• Small local models may not support tool calling well; leave Tool Use off for models that do not support it.
• Gateway login fails: check the current token and that both privileged intents are enabled and saved.
• Discord limits message length, so long streaming replies arrive as several messages.
• 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 Discord?

No. Discord bots connect out to the Discord gateway, so no public webhook URL is required.

Does the Discord bot support streaming replies?

Yes. Enable streaming on the bot; the AI back end must also stream. See the platform feature matrix for details.

Can the same Ollama 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 Discord setup guide
• Model configuration
• Other AI back ends on Discord: Dify · n8n · Coze · Langflow · DeepSeek
• Ollama on other platforms: Telegram · Slack · Lark (Feishu) · DingTalk · WeCom (internal app) · WeCom Intelligent Bot