AI Integrations
Deploy to Buddy with your favorite AI coding agents - pipelines, sandboxes, domains and logs from your terminal or editor.
Buddy's Remote MCP Server is available.
Pi + Buddy
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, so you can pair it with the provider of your choice. Paired with Buddy, it deploys your project, triggers and monitors pipelines, ships changes across environments, and digs through build output when something needs fixing.
Pi keeps a deliberately small toolset - read, write, edit and shell - which is why the CLI setup is the natural fit and MCP needs a community adapter. Staying model-agnostic means swapping providers changes nothing on the Buddy side.
Quick start
1 Install the Buddy CLInpm install -g bdy
2 Log in to Buddybdy login
3 Link your projectbdy proj link
4 Install the Buddy skillnpx skills add buddy/buddy-plugin
5 Start Pipi
The Buddy skill teaches the agent how to drive Buddy through the CLI, so you can ask for deployments and pipelines in your own words.
Example prompts
- “Create a snake app and deploy it for me”
- “Expose my app running locally on port 3000 to the internet”
- “Add a pipeline that runs on every change in the repository and executes my test suite”
- “Find the last successful production deployment and roll back to it”
Available commands
Connect MCP
Pi doesn't ship MCP support out of the box - add the community adapter first, then point it at Buddy's remote MCP server:
bashpi install npm:pi-mcp-adapter$
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" } } }