In this episode, we break down how to run multiple AI agents in a single codebase using Git worktrees. You’ll learn why naive repo cloning breaks down, how worktrees solve real-world workflow issues, and how to safely run parallel agents without stepping on each other’s changes.
Chapters:
Intro & Framing the Problem
Why Multi-Agent Repos Get Messy
Git Worktrees: The Core Idea
Naive Branch Cloning vs Worktrees
How Worktrees Work Under the Hood
Worktree Limitations & Gotchas
Running Parallel Agents Safely
Using Tmux for Multi-Agent Control
Best Practices & Wrap-Up
Check out our github: https://www.github.com/boundaryml/baml
AI That Works repo: https://github.com/ai-that-works/ai-that-works
Socials:
X: https://x.com/boundaryml
Discord: https://discord.com/invite/yzaTpQ3tdT
LinkedIn: https://www.linkedin.com/company/boundaryml/
Transcript
I've watched this one closely. Ask me anything about it and I'll point you to the exact moment.