---
title: Quickstart
description: Create your first Agent in minutes
icon: rocket
---

This guide will get you from zero to a running IronClaw instance in under 10 minutes

---

## Setting Up Your Agent

<Steps>

<Step title="Get IronClaw">

<Tabs>
  <Tab title="Agent Hub">
  Go to https://agent.near.ai/ and login with your preferred method, then create an IronClaw agent in a private instance.

  Once your private instance is ready, you can connect to your agent's private instance through `SSH` using the address provided in the [Agent Dashboard](https://agent.near.ai/):

  ```bash
  ssh -p <PORT> liquid-horse@agent2.near.ai
  ```

  <Accordion title="SSH Key">

  To use IronClaw, you will need to provide an SSH key. If you don't have one, you can generate it using the following command in your terminal:

  ```bash
  ssh-keygen -t rsa -b 4096 -C "you@example.com"
  cat ~/.ssh/id_rsa.pub
  ```

  </Accordion>

  <Accordion title="Issues Connecting?">
  Remember to add your SSH key to your device's SSH agent before connecting:

  ```bash
  ssh-add ~/.ssh/id_rsa
  ```

  </Accordion>
  </Tab>

  <Tab title="Local">
    Best for personal use on your own machine. Uses libSQL (embedded SQLite) — no separate database server required.

    ```bash
    # Install IronClaw
    curl --proto '=https' --tlsv1.2 -LsSf https://github.com/nearai/ironclaw/releases/latest/download/ironclaw-installer.sh | sh
    ```
  </Tab>
</Tabs>

</Step>

<Step title="Start the Agent">

Start your agent for the first time:

```bash
ironclaw
```

<Accordion title="⚠️ Error: Another IronClaw instance is already running">

If you get the error `Error: Another IronClaw instance is already running (PID 38). If this is incorrect, remove the stale PID file: /home/agent/.ironclaw/ironclaw.pid`, simply run the following command to remove the stale PID file and try starting the agent again:

```
# Remove the stale PID file
rm /home/agent/.ironclaw/ironclaw.pid

# Then start the agent again
ironclaw
```

</Accordion>

Since this is the first time you are starting your agent, it will ask you to configure your inference provider, and the LLM you want to use.

![setup](/images/quickstart/setup-wizard.png)

<Note>
We recommend using [NEAR AI](https://cloud.near.ai/) as your inference provider for maximum privacy and security, and the `Qwen3-30B` model for its cost-effectiveness
</Note>

<Accordion title="⚠️ Error: Failed to start webhook server">

If you encounter the error `Error: Channel webhook_server failed to start: Failed to bind to 0.0.0.0:8080: Address already in use (os error 98)`, simply try setting a different HTTP port:

```
# Change the default HTTP port to 8081
export HTTP_PORT=8081

# Then start the agent again
ironclaw
```

</Accordion>

</Step>

<Step title="Talk with your Agent">

Once your agent is up and running, you can start interacting with it through the terminal, simply type your message and the agent will respond

![hello-ai](/images/quickstart/hello-ai.png)


</Step>

<Step title="Update IronClaw">

Finally, make sure to regularly update IronClaw to get the latest features and improvements. You can update IronClaw by running the following command in your terminal:

```bash
ironclaw-update
```

</Step>

</Steps>


---

## Next Steps

Now that you have your agent up and running, it is time to configure a new [channel](./channels/telegram) to interact with your agent from your preferred messaging platform, and add some [tools](/extensions/web-search) to give your agent more capabilities.

<CardGroup cols={2}>
  <Card title="Channels" icon="plug" href="/channels/telegram">
    Connect your agent to your favorite messaging platform.
  </Card>

  <Card title="Tools" icon="wrench" href="/extensions/web-search">
    Give your agent access to external APIs and services.
  </Card>
</CardGroup>