Skip to content

autonomous para taxonomy: implementing context state management and graph clustering #7525

@thesohamdatta

Description

@thesohamdatta

hey team, we should integrate the para method (projects, areas, resources, archives) to stop omi from being just a pile of recordings.

the idea:

  • let the ai automatically tag things as a 'project' (active stuff), 'area' (ongoing), 'resource' (cool facts), or 'archive' (done).
  • group the app timeline by these projects so we can actually focus.
  • use the graph to show what's active. archive nodes should fade out so the brain view stays clean.

basically, omi should organize itself while we talk so we don't have to spend hours filing notes.

todo:

  • add para states to memories and graph nodes in the backend.
  • update the ai extraction to guess the right category based on deadlines/vibes.
  • build a dashboard in the app that bundles stuff by project.
  • make the graph dim out the archived stuff.

keep it simple, no manual filing, just speak and let omi handle the context.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions