Agents

Every agent below reaches Buddy through the same two pieces: the Buddy skill, which teaches it the bdy CLI, and the remote MCP server, which gives it direct API access. What differs per agent is where it runs, how you launch it, where its MCP configuration lives, and whether Buddy can also run it - as a pipeline action or inside a sandbox.

Pick your agent

Example prompts

Once an agent is running and your project is linked, these work the same way regardless of which one you picked:

• 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.

Which direction do you want?

• You prompt the agent - it lives on your machine or in its vendor's cloud and calls Buddy. That is what the pages above describe.
• Buddy prompts the agent - a pipeline action runs it on an event, with the repository, artifacts and variables of that run. Available for Claude Code, Antigravity, Codex CLI and Cursor.
• Buddy hosts the agent - a sandbox gives it a throwaway Ubuntu box with your repo fetched in, off your machine entirely.