A solo workflow for running Pi as a team of AI workers
Pi can be combined with Herdr and Gondolin to split one project across several AI agents. Herdr is used as the workspace, with the first tab acting as the that directs the rest. A custom extension called Herdr-control lets that create agents inside Gondolin micro VMs and place them into chosen Herdr workspaces, tabs, and panes.
The setup can group agents by role, such as three researcher panes in a research tab, four planner panes in a planning tab, and a worker in a worker area. The micro VMs are , but all agents share a so they can pass information to each other. Discussion around the setup raised an important missing detail: the model and cost matter, not just the tools.
One reply noted that the appears to show using Mimo 2.5.
Key points
- Pi is being used with Herdr and Gondolin to run several agents at once.
- One controls other agents and assigns them to specific tabs and panes.
- Gondolin micro VMs provide separated execution spaces for the agents.
- A lets the separated agents exchange information.
- Model choice and cost are still key details to check before copying the setup.