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

# Quickstart

> Install Bumblebee and talk to your first entity in five minutes.

## Requirements

* Python 3.11+
* [Ollama](https://ollama.com) installed
* [uv](https://docs.astral.sh/uv/) (recommended) or pip
* A GPU with 16 GB+ VRAM (see [Hardware](/reference/hardware))

## Install

<Steps>
  <Step title="Clone and install">
    ```bash theme={null}
    git clone https://github.com/Bumblebee-AGI/bumblebee.git
    cd bumblebee
    uv sync
    ```
  </Step>

  <Step title="Pull models">
    ```bash theme={null}
    ollama pull gemma4:26b        # chat and reasoning
    ollama pull nomic-embed-text   # memory similarity
    ```
  </Step>

  <Step title="Create your entity">
    Copy the example config:

    ```bash theme={null}
    cp configs/entities/canary.example.yaml configs/entities/canary.yaml
    ```

    Or run the guided wizard:

    ```bash theme={null}
    bumblebee create
    ```
  </Step>

  <Step title="Talk">
    ```bash theme={null}
    bumblebee talk canary --ollama
    ```

    The `--ollama` flag starts the Ollama server if it isn't running. Add `--pull-models` on a fresh machine to auto-download models.
  </Step>
</Steps>

## Run as a daemon

For always-on mode with all configured platforms (Telegram, Discord, CLI):

```bash theme={null}
bumblebee run canary --ollama
```

This starts the heartbeat daemon, soma body state, memory consolidation, proactive initiative, and every platform listed in your entity YAML.

## Next steps

<CardGroup cols={2}>
  <Card title="Entity configuration" icon="sliders" href="/guides/creating-entities">
    Understand the full entity YAML structure.
  </Card>

  <Card title="Setup & onboarding" icon="wand-magic-sparkles" href="/onboarding">
    Guided `bumblebee setup`, hybrid stack, tunnel automation, and Railway.
  </Card>

  <Card title="Telegram setup" icon="paper-plane" href="/guides/telegram">
    Connect your entity to a Telegram bot.
  </Card>

  <Card title="Local deployment" icon="server" href="/deployment/local">
    Tune Ollama, models, and local-only configuration.
  </Card>

  <Card title="Hybrid Railway" icon="cloud" href="/deployment/hybrid-railway">
    Home GPU + Railway worker + Postgres.
  </Card>

  <Card title="Architecture" icon="sitemap" href="/architecture/overview">
    How cognition, soma, identity, memory, and presence work together.
  </Card>
</CardGroup>