> ## Documentation Index
> Fetch the complete documentation index at: https://docs.novu.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect LangChain to Slack

> Add @novu/framework/langchain to an existing app, connect Slack, and return a LangChainAgentConfig from onMessage.

Connect a [LangChain](https://docs.langchain.com/) agent to Novu Connect. Return a `LangChainAgentConfig` from `onMessage`; Novu invokes the agent and delivers the reply on Slack. The same handler works on other providers after you link them.

This guide uses **Slack** first and assumes an existing Node.js app.

<Note>
  Starting from scratch? See [Scaffold with the CLI](#scaffold-with-the-cli).
</Note>

## Prerequisites

* A [Novu account](https://dashboard.novu.co)
* Node.js 22+
* An existing app with LangChain agent logic
* A Slack workspace where you can install apps
* An `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` (or another [LangChain provider](https://docs.langchain.com/oss/javascript/integrations/providers) key)

## Connect an existing app

<Steps>
  <Step>
    ## Create the agent and connect Slack

    In the [Novu dashboard](https://dashboard.novu.co):

    1. Go to **Agents** → **Create agent**.
    2. Under **Custom code**, pick **LangChain**.
    3. Set **Agent name** and **Identifier** (your code must use the same identifier).
    4. Select **Slack**, generate a [Slack App Configuration Token](https://api.slack.com/apps), paste it, and finish the install / Allow flow.

    Alternatively run `npx novu connect`, choose **LangChain** and **Slack**, and skip creating a starter project when prompted. Screenshots: [Create a Slack app](/agents/channels/slack#create-a-slack-app).
  </Step>

  <Step>
    ## Install packages

    <Tabs>
      <Tab title="OpenAI">
        ```bash theme={null}
        npm install @novu/framework langchain @langchain/core @langchain/openai
        ```
      </Tab>

      <Tab title="Claude">
        ```bash theme={null}
        npm install @novu/framework langchain @langchain/core @langchain/anthropic
        ```
      </Tab>
    </Tabs>

    Add to `.env.local`:

    ```bash theme={null}
    NOVU_SECRET_KEY=your-novu-secret-key
    OPENAI_API_KEY=sk-...   # or ANTHROPIC_API_KEY
    ```
  </Step>

  <Step>
    ## Add the handler

    Create `app/novu/agents/<your-identifier>.ts`. Match `agent('...')` to the dashboard **Identifier**.

    <Tabs>
      <Tab title="OpenAI">
        ```typescript theme={null}
        import { agent } from '@novu/framework/langchain';

        export const supportBot = agent('support-bot', {
          onMessage: async (_message, ctx) => ({
            model: 'openai:gpt-4o',
            system: 'You are a helpful support agent. Keep answers short.',
          }),
        });
        ```
      </Tab>

      <Tab title="Claude">
        ```typescript theme={null}
        import { agent } from '@novu/framework/langchain';

        export const supportBot = agent('support-bot', {
          onMessage: async (_message, ctx) => ({
            model: 'anthropic:claude-sonnet-4-20250514',
            system: 'You are a helpful support agent. Keep answers short.',
          }),
        });
        ```
      </Tab>
    </Tabs>

    Export from `app/novu/agents/index.ts`:

    ```typescript theme={null}
    export { supportBot } from './support-bot';
    ```

    Returning `{ model, system }` is a `LangChainAgentConfig`. Novu calls `createAgent().invoke()` and posts the final text. Novu maps `ctx.history` on this path.

    On Next.js, add LangChain packages to `serverExternalPackages` for Turbopack. See [Next.js and Turbopack](/agents/custom-code-agent/frameworks/langchain#next-js-and-turbopack).
  </Step>

  <Step>
    ## Add the bridge route

    ```typescript theme={null}
    import { serve } from '@novu/framework/next';
    import { supportBot } from '../../novu/agents';

    export const { GET, POST, OPTIONS } = serve({
      agents: [supportBot],
    });
    ```

    For Express, Hono, and other servers, see [Connecting your app](/agents/custom-code-agent/connecting-your-app).
  </Step>

  <Step>
    ## Run locally and message Slack

    ```bash theme={null}
    npx novu dev --port 4000
    ```

    DM or @mention the bot in Slack. The reply should come from your LangChain handler in the same thread.
  </Step>
</Steps>

## Tool approval

Gate a tool with `needsApproval`:

```typescript theme={null}
import { tool } from '@langchain/core/tools';
import { agent } from '@novu/framework/langchain';
import { z } from 'zod';

const issueRefund = tool(
  async ({ orderId }) => ({ orderId, status: 'refunded' }),
  {
    name: 'issueRefund',
    description: 'Issue a refund for an order',
    schema: z.object({ orderId: z.string() }),
  },
);

export const supportBot = agent('support-bot', {
  onMessage: async (_message, ctx) => ({
    model: 'openai:gpt-4o',
    system: 'You are a helpful support agent. Use issueRefund only when the user asks for a refund.',
    tools: [issueRefund],
    needsApproval: (toolCall) => toolCall.name === 'issueRefund',
  }),
});
```

See [Tool approval](/agents/custom-code-agent/building-blocks/tool-approval) and the [LangChain reference](/agents/custom-code-agent/frameworks/langchain#automatic-tool-approval).

## Scaffold with the CLI

```bash theme={null}
npx novu connect
```

Choose **LangChain**, authenticate the model, connect **Slack**, and accept the starter project. Then run `npm run dev:novu`.

For an existing codebase, use [Connect an existing app](#connect-an-existing-app) instead.

## FAQ

<AccordionGroup>
  <Accordion title="Which channels work with a LangChain agent?">
    Slack, Microsoft Teams, WhatsApp, Telegram, and email. See [Channels overview](/agents/channels/overview).
  </Accordion>

  <Accordion title="Does Novu run LangChain for me?">
    When you return a `LangChainAgentConfig`, Novu invokes `createAgent()` with your model, system prompt, and tools, then posts the final text.
  </Accordion>

  <Accordion title="Where is the adapter API documented?">
    [LangChain reference](/agents/custom-code-agent/frameworks/langchain): tool approval, custom invoke, and `onError`.
  </Accordion>

  <Accordion title="I get &#x22;Cannot find module as expression is too dynamic&#x22;">
    Turbopack cannot resolve LangChain dynamic provider imports for model strings. Add LangChain packages to `serverExternalPackages` in `next.config.mjs`. See [Next.js and Turbopack](/agents/custom-code-agent/frameworks/langchain#next-js-and-turbopack).
  </Accordion>
</AccordionGroup>

## Set this up with an AI assistant

<Prompt description="Connect my LangChain agent to Slack with Novu" icon="plug" actions={["copy", "cursor"]}>
  # Connect a LangChain agent to Slack with Novu Connect

  Follow [https://docs.novu.co/agents/get-started/langchain](https://docs.novu.co/agents/get-started/langchain)

  ## Goal

  Add Novu bridge + LangChain config handler to this repo and connect Slack. Prefer the existing project over scaffolding a new one.

  ## Rules

  ALWAYS:

  * Match `agent('id')` to the Novu dashboard agent Identifier
  * Return a LangChainAgentConfig so Novu can invoke the agent
  * Keep handlers channel-agnostic
  * Follow the project's package manager and TypeScript conventions

  NEVER:

  * Hardcode API keys
  * Rebuild conversation history manually when returning a config
</Prompt>

## Next steps

<Columns cols={2}>
  <Card icon="link" href="/agents/custom-code-agent/frameworks/langchain" title="LangChain reference">
    Adapter API: tools, approval, custom invoke, and onError.
  </Card>

  <Card icon="hash" href="/agents/channels/slack" title="Slack">
    Slack capabilities and setup links.
  </Card>

  <Card icon="rocket" href="/agents/custom-code-agent/going-to-production" title="Going to production">
    Deploy the bridge and disable local tunneling.
  </Card>

  <Card icon="sparkles" href="/agents/get-started/ai-sdk" title="Connect AI SDK">
    Same flow with @novu/framework/ai-sdk.
  </Card>
</Columns>