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

# Multi-Bot

> Two independent Slack bots on the same workspace with separate prefixes, tokens, and session isolation

## Code

```python multi_bot.py theme={null}
from os import getenv

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIChat
from agno.os.app import AgentOS
from agno.os.interfaces.slack import Slack

db = SqliteDb(session_table="agent_sessions", db_file="tmp/multi_bot.db")

ace_agent = Agent(
    id="ace",
    name="Ace",
    model=OpenAIChat(id="gpt-4.1-mini"),
    db=db,
    instructions=[
        "You are Ace, a research assistant. Always introduce yourself as Ace.",
        "When answering, cite sources and be thorough.",
    ],
    add_history_to_context=True,
    num_history_runs=5,
    markdown=True,
)

dash_agent = Agent(
    id="dash",
    name="Dash",
    model=OpenAIChat(id="gpt-4.1-mini"),
    db=db,
    instructions=[
        "You are Dash, a concise summarizer. Always introduce yourself as Dash.",
        "Keep answers concise - 2-3 sentences max.",
    ],
    add_history_to_context=True,
    num_history_runs=5,
    markdown=True,
)

agent_os = AgentOS(
    agents=[ace_agent, dash_agent],
    interfaces=[
        Slack(
            agent=ace_agent,
            prefix="/ace",
            token=getenv("ACE_SLACK_TOKEN"),
            signing_secret=getenv("ACE_SLACK_SIGNING_SECRET"),
            streaming=True,
            reply_to_mentions_only=False,
        ),
        Slack(
            agent=dash_agent,
            prefix="/slack",
            token=getenv("DASH_SLACK_TOKEN"),
            signing_secret=getenv("DASH_SLACK_SIGNING_SECRET"),
            streaming=True,
            reply_to_mentions_only=False,
        ),
    ],
)
app = agent_os.get_app()

if __name__ == "__main__":
    agent_os.serve(app="multi_bot:app", reload=True)
```

## Usage

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Set Environment Variables">
    ```bash theme={null}
    # Ace bot credentials
    export ACE_SLACK_TOKEN=xoxb-ace-bot-token
    export ACE_SLACK_SIGNING_SECRET=ace-signing-secret

    # Dash bot credentials
    export DASH_SLACK_TOKEN=xoxb-dash-bot-token
    export DASH_SLACK_SIGNING_SECRET=dash-signing-secret

    export OPENAI_API_KEY=your-openai-api-key
    ```
  </Step>

  <Step title="Install Dependencies">
    ```bash theme={null}
    uv pip install -U "agno[slack]" openai
    ```
  </Step>

  <Step title="Configure Slack Apps">
    Create two Slack apps in your workspace. Set their Event Subscription URLs to different prefixes on the same server:

    * Ace: `https://<your-tunnel>/ace/events`
    * Dash: `https://<your-tunnel>/slack/events`
  </Step>

  <Step title="Run Example">
    ```bash theme={null}
    python multi_bot.py
    ```
  </Step>
</Steps>

## Key Features

* **Multiple Bots, One Server**: Two Slack apps served from a single AgentOS instance using different URL prefixes
* **Per-Bot Credentials**: Each Slack interface uses its own token and signing secret via environment variables
* **Session Isolation**: Both bots share a SQLite database but maintain separate sessions per agent ID
* **Streaming Responses**: Both bots stream their responses in real time