The octopus architecture for AI agents
Key takeaways
- The octopus architecture describes a system with a central coordinating brain that dispatches to semi-autonomous sub-brains.
- This architecture was born from a series of dead-ends and iterative improvement.
- Plugins can contribute others, like the Google Workspace lane.
The octopus architecture describes a system with a central coordinating brain that dispatches to semi-autonomous sub-brains.
Tork Bot is designed a bit like an octopus. This architecture was born from a series of dead-ends and iterative improvement. When I say octopus, what I mean is that Tork Bot has a centralized “brain” directing many semi-autonomous appendages, each with their own brains, reporting back to the central dispatcher.
Static lanes are the long-lived appendages. Curator is one. Plugins can contribute others, like the Google Workspace lane. Lane templates are different. A template is a capability that can be instantiated for a bounded purpose. A sandbox snapshot is different again: it is not a collaborator at all, just a saved filesystem starting point for a future sandbox-backed lane.