Working on Juju with Agents

[gfouillet (Guillame Fouillet)]

I have written an helper to help using this approach with worktree:

Automated worktrees for multi-agent Juju development

Running multiple AI agents on Juju without isolation is like letting five people share one clipboard. It works until someone overwrites the wrong bootstrap, and then you spend your afternoon debugging whose JUJU_DATA is whose instead of actually fixing anything. The solution is well-known: each agent needs its own JUJU_DATA, its own GOBIN, its own view of the world. Joseph Phillips wrote a great post on how he approaches this, using four full clones and direnv. If you haven’t read it, stop and …

This works with Juju, but the tool is designed to be quite adaptable