# Pi

Use Pi with Buddy to deploy your project, trigger and monitor pipelines, and dig through build logs from your terminal.

Pi is an open-source AI coding agent that lives in your terminal. Built on a small, focused toolset - read, write, edit, and shell - it works with the full context of your project and stays model-agnostic, letting you pair it with Anthropic, OpenAI, Google, xAI, and other providers. Paired with Buddy, Pi can deploy your project and let Buddy handle the entire deployment workflow. On top of that, it can trigger and monitor your pipelines, ship changes across environments, and dig through build output and logs when something needs fixing.

<Hint type="info">
This page covers working with Buddy from within Pi. On top of that, you can run AI coding agents in a fully isolated Buddy sandbox - see [Run agents in a sandbox](/docs/ai-agents/sandboxes.md).
</Hint>

## Quick start

<Steps>
  <Step title="Install the Buddy CLI">
    ```bash
    npm install -g bdy
    ```
  </Step>
  <Step title="Log in to Buddy">
    ```bash
    bdy login
    ```
  </Step>
  <Step title="Link your project">
    Run this inside your project directory to connect it to a Buddy project:

    ```bash
    bdy proj link
    ```
  </Step>
  <Step title="Install the Buddy skill">
    ```bash
    npx skills add buddy/buddy-plugin
    ```
  </Step>
  <Step title="Start Pi">
    ```bash
    pi
    ```
  </Step>
  <Step title="Prompt the agent">
    Ask it to build and ship something end to end, for example:

    ```text
    Create a snake app and deploy it for me
    ```
  </Step>
</Steps>

## Example prompts

Once the agent is running and your project is linked to Buddy, try prompts like:

- Create a Next.js app and deploy it to production.
- Deploy an Umami analytics instance and wire it into my app.
- Deploy an AI chatbot with Postgres for history and Redis for rate limiting.
- Deploy my app, set up a CDN, and buy and configure a domain with SSL.
- Add a pipeline that runs on every change in the repository and executes my test suite.
- Add a pipeline that runs every minute, checks that my site is up, and sends a notification to Slack, email, Telegram, or SMS if anything is wrong.
- Check the last few CI pipeline runs for failures, read the logs, and fix the failing tests.
- Analyze the logs from the last production deployment and fix the errors.
- Find the last successful production deployment and roll back to it.
- Check my app logs and open issues based on what you find.

## Connect MCP

Give Pi access to Buddy over MCP so it can run pipelines, manage deployments, and read logs. See the [MCP](/docs/ai-agents/mcp.md) page for the regional server URLs and how to filter the exposed tool categories.

Pi doesn't ship MCP support out of the box - add it with the community [`pi-mcp-adapter`](https://github.com/nicobailon/pi-mcp-adapter):

```bash
pi install npm:pi-mcp-adapter
```

Then add the server to `~/.config/mcp/mcp.json` (or `.mcp.json` in your project) and restart Pi:

```json
{
  "mcpServers": {
    "buddy": {
      "url": "https://mcp.buddy.works/mcp"
    }
  }
}
```


---
Original source: https://buddy.works/docs/ai-agents/agents/pi